cleveragents/cleveragents-core

Fork 3

Files

T

freemo 277db70333

Docs: Cleaned up a lot of the CLI command structure to make it a bit more lean

2026-02-09 21:24:07 -05:00

513 KiB

Raw Blame History

CleverAgents Documentation (Detailed Spec)

Key Themes

Key themes include:

A four-phase plan lifecycle (Action → Strategize → Execute → Apply).
Actors as a unifying abstraction (an LLM/agent or a whole graph).
A sandbox + diff review workflow and CLI-first interaction model.
A scalable context/memory architecture (hot/warm/cold tiers, per-actor views).
Invariants as first-class constraints (global, project, action, and plan scoped) that flow into the decision tree, with precedence-based conflict resolution via the Invariant Reconciliation Actor.
A future-facing correction model where the user can "edit the decision tree" and only recompute affected subtrees.

Big Picture: What CleverAgents is

CleverAgents is your command center for AI agents—a unified platform for orchestrating any task you want agents to accomplish, from developing large software projects to writing comprehensive technical papers, administering databases, managing cloud infrastructure, or any complex multi-step workflow. The core value proposition is enabling long-running, complex, large-scale tasks to execute autonomously with minimal human intervention, making it ideal for building entire software systems, producing extensive documentation, or managing sophisticated operations largely hands-off.

In server mode, CleverAgents becomes a collaborative hub where teams can share resources—prompts, actors, actions, and projects—while executing plans in the cloud. This enables a consistent experience across all your devices: start a complex task on your laptop, check progress from your phone, and review results from any machine.

While CleverAgents leverages LangGraph and LangChain for the underlying LLM runtime primitives (tool calling, graphs, routing), its value lies in what it builds on top:

CleverAgents provides:

A first-class plan lifecycle (Action/Strategize/Execute/Apply) for breaking down and tracking complex work,
A project + resource model for grounding tasks in real codebases, databases, documents, and infrastructure,
A consistent actor abstraction for defining and composing intelligent agents,
An independently registered resource abstraction for representing anything that can be read, written, or queried,
An independently registered tool abstraction for reusable, callable operations with resource bindings,
A consistent skill abstraction for organizing tools into composable capability collections,
A sandbox + checkpoint safety model for safe, reversible execution,
A CLI/TUI/Web UX for controlling and monitoring large multi-step autonomous work.

Glossary (Terms Used Precisely)

Plan: A tracked lifecycle for a single unit-of-work (which may spawn child plans). Plans follow the same namespace rules as actors.
Action: A reusable plan template not tied to any project yet. Created via CLI commands (not YAML files). Actions follow the same namespace rules as actors.
Strategize: Read-only planning phase that produces a strategy and child plan blueprint. All decisions are made during this phase.
Execute: Phase that performs work in a sandbox; spawns child plans (based on decisions made in Strategize); produces artifacts/diffs.
Apply: Phase that commits sandbox results into the real project (and records an "applied" plan state).
Project: A collection of linked resources + configuration that define "where work happens" and "what can be touched." Created via CLI commands. Projects link to independently registered resources from the Resource Registry (they do not define resources inline). A resource can be linked to multiple projects. Can be local (contains local-only resources) or remote (all resources remotely accessible).
Resource: A namespaced, independently registered entity representing anything that can be read, written, or queried. Resources are managed through the agents resource CLI commands and stored in the Resource Registry. Each resource has a resource type that determines its properties, allowed parent/child relationships, sandbox strategy, and handler. Resources form a directed acyclic graph (DAG) with parent/child relationships. Resources are either physical (a specific, concrete manifestation — THIS file at THIS path, THIS git repository at THIS URL, THIS commit in THIS repo) or virtual (an abstract identity linking equivalent physical resources — "these two fs-file resources and this git-tree-entry resource all represent the same file with the same content, name, and permissions"). Two physical resources share a virtual parent when they are equivalent by the virtual type's criteria; when equivalence breaks, the virtual relationship is updated. Resources follow the same <namespace>/<name> naming convention as other entities. Extends the MCP resource concept to support both read and write operations.
Resource Type: A schema-level definition that constrains a category of resources. A resource type defines: what CLI arguments agents resource add <type> accepts, whether instances are physical or virtual, what child/parent resource types are allowed, what child resources are auto-discovered when an instance is created, the sandbox strategy, and the resource handler implementation. Built-in physical types span three layers: git metadata (git, git-remote, git-branch, git-tag, git-commit, git-tree, git-tree-entry, git-stash, git-submodule), git checkout (git-checkout), and filesystem (fs-mount, fs-directory, fs-file, fs-symlink, fs-hardlink). Built-in virtual types (file, directory, symlink, commit, branch, tag, remote, submodule, tree) link equivalent physical resources through content/identity matching. Custom types are defined in YAML configuration files and registered via agents resource type add. Resource types also specify whether instances can be created directly by users (user_addable: true) or are only auto-generated as children of other resources.
Physical Resource: A resource representing a specific, concrete manifestation — a particular file at a particular path, a particular git repository at a particular URL, a particular commit in a particular repo. Physical resources exist somewhere (locally on disk, or remotely on a server) and can be directly read and written by tools. Every physical resource is a distinct instance, even if its content is identical to another physical resource. A physical resource's parents can be either physical or virtual resources.
Virtual Resource: A resource representing an abstract identity that links equivalent physical resources. Virtual resources have no location of their own — they serve as shared parents of physical resources that are "the same" by some equivalence criterion (same content, same name, same permissions, same hash, etc.). Not all physical resources have a virtual parent. The children of a virtual resource can be physical resources, other virtual resources, or both. Built-in virtual types use simple names that mirror their physical counterparts: file (links fs-file + git-tree-entry with same content, filename, and permissions), directory (links fs-directory + git-tree with same recursive content), symlink (links fs-symlink + git-tree-entry mode 120000 with same target), commit (links git-commit across repos with same commit hash), branch (links git-branch across repos with same name and HEAD), tag (links git-tag across repos with same name and target), remote (links git-remote across repos with same URL), submodule (links git-submodule across repos with same URL and path), tree (links git-tree across repos with same tree hash).
Resource Binding: The declared association between a tool and the resources it operates on. A tool declares resource slots — typed placeholders specifying what resource types the tool requires (e.g., "I need a git-checkout resource with read_write access"). Slots are resolved to actual resources at activation time (contextual binding — from the plan's project), at registration time (static binding — hardcoded to a specific resource), or at invocation time (parameter binding — passed as a tool argument).
Resource Registry: A persistent catalog of all independently registered resources and their DAG relationships (parent/child links). Managed via agents resource add/remove/list/show CLI commands. The Resource Registry works alongside the Tool Registry and Skill Registry.
Skill: A namespaced, reusable collection of tools registered in the system via its own YAML configuration file and managed through the agents skill CLI commands. A skill assembles tools by referencing named tools from the Tool Registry, defining anonymous inline tools, and/or including other skills (whose tools are merged in). Skills can also expose tools from MCP servers, Agent Skills Standard folders, and built-in tool groups. When referencing named tools or including sub-skills, metadata can optionally be overridden. Actors reference skills by fully-qualified name. Extends the MCP standard and Agent Skills standard. Skills follow the same namespace rules as actors, tools, actions, etc.
Tool: A namespaced, independently registered, callable operation. A tool is the atomic unit of execution — it has a name, a JSON Schema for inputs/outputs, capability metadata (read-only, writes, checkpointable, etc.), and a uniform lifecycle (discover, activate, execute, deactivate). Tools are defined in their own YAML configuration files and managed through the agents tool CLI commands, following the same <namespace>/<name> naming convention as other entities. Tools originate from one of four sources: MCP servers (exposed via JSON-RPC tools/call), Agent Skills Standard folders (instruction-driven SKILL.md bundles), built-in operations (first-party file, git, search, and directory operations), or custom code (Python). Tools have a dual role: they can be included in skills (by reference) to form reusable capability collections, and they can be used directly as tool nodes in actor graphs. When referencing a named tool in a skill or actor, its metadata can optionally be overridden at the point of use.
Anonymous Tool: An inline tool definition (Python code block) that appears directly inside a skill YAML or an actor graph node. Anonymous tools use the same format as a named tool's YAML definition but lack a namespaced name — they are not registered in the Tool Registry, cannot be reused across skills or actors, and exist only within the scope where they are defined. Anonymous tools are useful for one-off, context-specific operations.
Actor: Anything conversational; may be a single agent/LLM or an entire graph of actors/tools. Defined via YAML configuration files (LangGraph definitions). Always named using <namespace>/<name> format.
Session: A user interaction context and conversation thread that can span multiple plans.
Server: Optional shared service for multi-user storage, permissions, and orchestration. Plans on remote projects can execute on the server.
Namespace: Scoping mechanism for actors, tools, skills, resources, resource types, actions, plans, etc. local/ is reserved for local-only items. User namespaces (<username>/) and organization namespaces (<orgname>/) are stored on the server. Built-in LLM actors use provider namespaces (e.g., openai/, anthropic/). Built-in resource types use no namespace prefix (e.g., git, git-checkout, fs-mount, fs-directory, file, commit).
Decision: A recorded choice point made during Strategize that affects downstream work. Decisions form a tree structure that enables correction and replay.
Invariant: A named constraint or rule that applies to plan execution. Invariants can be attached at four scopes: global (applies to all plans), project (applies to all plans targeting that project), plan (applies to a specific plan and its child plans), or action (carried forward as plan-level invariants when the action is used). Managed via the unified agents invariant add/list/remove command, or attached at creation time via --invariant flags on agents project create, agents action create, and agents plan use. Precedence: plan-level invariants override project-level, which override global-level, when conflicts exist. An Invariant Reconciliation Actor (set via --invariant-actor on actions, plans, and projects, or globally via agents config set invariant-actor) resolves conflicts and computes the effective invariant view when a plan enters Strategize. During Strategize, the effective invariants are recorded as invariant_enforced decisions in the decision tree. When a top-level plan spawns child plans, the parent's effective invariant view is passed down to each child plan.
ULID: Universally Unique Lexicographically Sortable Identifier. Preferred over UUID for plan and decision IDs due to time-sortability.

CLI Commands

Command Synopsis

agents|cleveragents [--data-dir PATH] [--config-path PATH] [--help] [--version]
                     [--install-completion [SHELL]] [--show-completion [SHELL]]
                     <command> [args]

agents version
agents info
agents diagnostics
agents init [--yes]

agents session create [--name NAME] [--actor ACTOR] [--metadata KEY=VALUE ...]
agents session list [--format table|json]
agents session show <SESSION_ID|NAME>
agents session delete <SESSION_ID|NAME> [--yes]
agents session export <SESSION_ID|NAME> --output FILE
agents session import --input FILE [--name NAME]
agents session tell "<prompt>" [--session SESSION_ID|NAME] [--actor ACTOR] [--stream]

agents project create --name/-n NAME [--description/-d TEXT]
                     [--invariant TEXT ...] [--invariant-actor ACTOR]
agents project link-resource --project/-p PROJECT --resource/-r RESOURCE [--read-only] [--alias ALIAS]
agents project unlink-resource --project/-p PROJECT --resource/-r RESOURCE [--yes]
agents project list [--namespace/-n NS] [--format table|json]
agents project show <NAME> [--format rich|json]
agents project set-validation --project/-p PROJECT [--resource NAME]
                          [--test-command CMD] [--lint-command CMD]
                          [--type-check-command CMD] [--build-command CMD]
                          [--timeout SECONDS] [--clear]
agents project delete <NAME> [--force/-f] [--yes]
agents project context set --project PROJECT
                          [--view strategize|execute|apply|default]
                          [--include-resource NAME ...]
                          [--exclude-resource NAME ...]
                          [--include-path GLOB ...]
                          [--exclude-path GLOB ...]
                          [--hot-max-tokens N]
                          [--warm-max-decisions N]
                          [--cold-max-decisions N]
                          [--query-limit N]
                          [--max-file-size BYTES]
                          [--max-total-size BYTES]
                          [--summarize/--no-summarize]
                          [--summary-max-tokens N]
                          [--clear]
agents project context show --project PROJECT [--view strategize|execute|apply|default]
                          [--format table|json]

agents actor run --config/-c FILE... --prompt/-p TEXT [--output/-o FILE]
                [--verbose/-v] [--unsafe/-u] [--context NAME]
                [--context-dir PATH] [--load-context FILE]
                [--temperature/-t FLOAT] [--allow-rxpy-in-run-mode]
agents actor add <NAME> --config/-c FILE [--unsafe] [--set-default] [--option/-o key=value ...]
agents actor update <NAME> [--config/-c FILE] [--unsafe|--safe] [--set-default]
                 [--option/-o key=value ...]
agents actor remove <NAME>
agents actor list
agents actor show <NAME>
agents actor set-default <NAME>
agents actor context add --name NAME <PATHS...> [-r/--recursive]
agents actor context load --name NAME <PATHS...> [-r/--recursive]
agents actor context rm --name NAME <PATHS...>
agents actor context list [NAME] [--format table|json]
agents actor context show --name NAME [PATH]
agents actor context export --name NAME --output FILE
agents actor context import --name NAME --input FILE
agents actor context delete --name NAME [--yes]
agents actor context clear --name NAME [--yes]

agents skill add <NAME> --config/-c FILE [--description/-d TEXT] [--upgrade]
agents skill remove <NAME> [--yes]
agents skill list [--namespace/-n NS] [--source SOURCE] [--format table|json]
agents skill show <NAME> [--format rich|json]
agents skill tools <NAME> [--format table|json]

agents tool add <NAME> --config/-c FILE [--description/-d TEXT] [--upgrade]
agents tool remove <NAME> [--yes]
agents tool list [--namespace/-n NS] [--source SOURCE] [--format table|json]
agents tool show <NAME> [--format rich|json]

agents resource type add <NAME> --config/-c FILE [--upgrade]
agents resource type remove <NAME> [--yes]
agents resource type list [--format table|json]
agents resource type show <NAME> [--format rich|json]

agents resource add [--description/-d TEXT] [--upgrade] <TYPE> <NAME> [type-specific-flags...]
agents resource remove <NAME> [--yes]
agents resource list [--namespace/-n NS] [--type/-t TYPE] [--format table|json]
agents resource show <NAME> [--format rich|json]
agents resource tree <NAME> [--depth/-d N] [--type/-t TYPE] [--format tree|json]
agents resource link-child --parent/-p RESOURCE --child/-c RESOURCE
agents resource unlink-child --parent/-p RESOURCE --child/-c RESOURCE [--yes]

agents plan list [--phase PHASE] [--state STATE] [--project PROJECT]
                [--action ACTION] [--format table|json]
agents plan use <ACTION_NAME> --project/-p PROJECT [--project/-p PROJECT ...]
               [--arg/-a name=value ...]
               [--automation-level manual|review|auto]
               [--safety-profile NAME]
               [--require-sandbox/--no-require-sandbox]
               [--require-checkpoints/--no-require-checkpoints]
               [--require-apply-approval/--no-require-apply-approval]
               [--allow-skill-category NAME ...]
               [--deny-skill-category NAME ...]
               [--invariant TEXT ...]
               [--strategy-actor/-s ACTOR]
               [--execution-actor/-e ACTOR]
               [--estimation-actor ACTOR]
               [--invariant-actor ACTOR]
agents plan execute [PLAN_ID]
agents plan apply <PLAN_ID> [--yes]
agents plan status [PLAN_ID]
agents plan cancel <PLAN_ID> [--reason/-r TEXT]
agents plan tree [PLAN_ID] [--format tree|json|flat] [--show-superseded]
agents plan explain <DECISION_ID> [--show-context] [--show-reasoning]
agents plan correct <DECISION_ID> --mode revert|append --guidance/-g TEXT
                   [--dry-run] [--yes]
agents plan diff --plan <PLAN_ID>
agents plan diff --correction <CORRECTION_ATTEMPT_ID>
agents plan artifacts <PLAN_ID>
agents plan prompt <PLAN_ID> "<GUIDANCE>"
agents plan resume <PLAN_ID>
agents plan rollback <PLAN_ID> <CHECKPOINT_ID> [--yes]

agents action create <NAME>
  --strategy-actor/-s ACTOR
  --execution-actor/-e ACTOR
  --definition-of-done/-d TEXT
  [--description TEXT]
  [--long-description TEXT]
  [--arg/-a spec ...]
  [--reusable/--no-reusable]
  [--read-only]
  [--available]
  [--estimation-actor ACTOR]
  [--invariant-actor ACTOR]
  [--safety-profile NAME]
  [--require-sandbox/--no-require-sandbox]
  [--require-checkpoints/--no-require-checkpoints]
  [--require-apply-approval/--no-require-apply-approval]
  [--allow-skill-category NAME ...]
  [--deny-skill-category NAME ...]
  [--invariant TEXT ...]
agents action list [--namespace/-n NS] [--state/-s STATE] [--available]
agents action show <ACTION_ID|NAME>
agents action available <ACTION_ID|NAME>
agents action archive <ACTION_ID|NAME>

agents config set <key> <value>
agents config get <key>
agents config list
agents providers list

agents invariant add "<TEXT>" [--global] [--project/-p PROJECT] [--plan PLAN_ID] [--action ACTION]
agents invariant list [--global] [--project/-p PROJECT] [--plan PLAN_ID] [--action ACTION]
                     [--effective] [--format table|json]
agents invariant remove <INVARIANT_ID> [--yes]

Command Reference

Global Options

Purpose Configure global state locations and shell integration for every command.

Arguments

--data-dir PATH: Overrides the global data directory (database, caches, sessions, logs). When omitted, the default data location is used.
--config-path PATH: Overrides the global configuration file path. When omitted, the default config path is used.
--help, -h: Print help for the current command.
--version, -V: Print the version and exit.
--install-completion [SHELL]: Install shell completion for the given shell.
--show-completion [SHELL]: Show the completion script for the given shell.

Examples

$ agents --data-dir /srv/cleveragents --config-path /srv/cleveragents/config.toml info ╭─ System Snapshot ─────────────────╮ │ CleverAgents 1.0.0 │ │ Mode: local │ │ Automation: review │ │ Default Actor: local/orchestrator │ │ Status: ready │ ╰───────────────────────────────────╯ ╭─ Paths ───────────────────────────────╮ │ Data Dir: /srv/cleveragents │ │ Config: /srv/cleveragents/config.toml │ │ Logs: /srv/cleveragents/logs │ │ Cache: /srv/cleveragents/cache │ │ Database: /srv/cleveragents/agents.db │ ╰───────────────────────────────────────╯ ╭─ Runtime ──────────╮ │ PID: 4127 │ │ Uptime: 00:14:32 │ │ Python: 3.13.1 │ │ Host: devbox.local │ │ Platform: linux │ ╰────────────────────╯ ╭─ Projects & Sessions ─╮ │ Projects: 2 │ │ Sessions: 1 active │ │ Active Plans: 0 │ │ Actors: 3 │ ╰───────────────────────╯

✓ OK Environment loaded

agents version

Purpose Print the current CLI version.

Arguments

None.

Examples

$ agents version ╭─ CLI Version ────╮ │ CleverAgents CLI │ │ Version: 1.0.0 │ │ Channel: stable │ │ Python: 3.13 │ ╰──────────────────╯ ╭─ Build ────────────────╮ │ Build Date: 2026-02-08 │ │ Commit: a17c3f9 │ │ Schema: v3 │ │ Platform: linux-x86_64 │ ╰────────────────────────╯ ╭─ Dependencies ─────────────────╮ │ LangGraph: 0.2.60 │ │ LangChain: 0.3.18 │ │ MCP SDK: 1.4.0 │ │ Pydantic: 2.10.4 │ ╰────────────────────────────────╯

✓ OK Version reported

agents info

Purpose Show configuration and runtime information useful for debugging or support.

Arguments

None.

Examples

$ agents info ╭─ Environment ───────────────────────────────────────────────╮ │ Data Dir: /home/alex/.cleveragents │ │ Config: /home/alex/.cleveragents/config.toml │ │ Database: sqlite:///home/alex/.cleveragents/cleveragents.db │ │ Server Mode: disabled │ │ Platform: Linux 6.8.0 (x86_64) │ ╰─────────────────────────────────────────────────────────────╯ ╭─ Runtime ─────────────────────────╮ │ Default Actor: local/orchestrator │ │ Automation: review │ │ Providers: 3 configured │ │ Sessions: 2 active │ │ Active Plans: 1 │ ╰───────────────────────────────────╯ ╭─ Storage ─────╮ │ Cache: 118 MB │ │ Logs: 42 MB │ │ Backups: 3 │ │ DB Size: 8 MB │ ╰───────────────╯ ╭─ Indexing ─────────────╮ │ Text Index: ready │ │ Vector Index: ready │ │ Graph Store: disabled │ │ Indexed Files: 1,247 │ ╰────────────────────────╯

✓ OK Environment details ready

agents diagnostics

Purpose Run health checks for configuration, providers, and filesystem permissions.

Arguments

None.

Examples

$ agents diagnostics ╭─ Checks ────────────────────────────────╮ │ Check Status Details │ │ ─────────────── ────── ────────────── │ │ Config file OK readable │ │ Database OK writable │ │ OPENAI_API_KEY WARN missing │ │ Anthropic key OK configured │ │ Disk space OK 2.1 GB free │ │ Text index OK tantivy 0.22 │ │ Vector index OK faiss (CPU) │ │ Graph store WARN not configured │ │ File permissions OK data dir r/w │ │ Git OK git 2.43.0 │ ╰────────────────────────────────────────╯ ╭─ Summary ────────╮ │ Checks: 10 total │ │ Warnings: 2 │ │ Errors: 0 │ │ Duration: 0.6s │ ╰──────────────────╯ ╭─ Recommendations ─────────────────────────────────────────────╮ │ - Set OPENAI_API_KEY to enable OpenAI models │ │ - Configure a graph store backend for structural code queries │ │ - Run agents providers list to verify credentials │ ╰───────────────────────────────────────────────────────────────╯

⚠ WARN 2 warnings require attention

agents init

Purpose Initialize or reset the global CleverAgents environment. This wipes any existing data and re-creates the global config and database.

Arguments

--yes: Skip the confirmation prompt and proceed with the wipe.

Examples

$ agents init Warning: This will remove all data in /home/alex/.cleveragents Continue? [y/N]: y ╭─ Environment Reset ────────────────────────────────╮ │ Config: /home/alex/.cleveragents/config.toml │ │ Database: /home/alex/.cleveragents/cleveragents.db │ │ Backup: /home/alex/.cleveragents.backup-2026-02-08 │ │ Status: ready │ ╰────────────────────────────────────────────────────╯ ╭─ Defaults ────────────────────────╮ │ Default Actor: local/orchestrator │ │ Automation: review │ │ Sandbox: required │ │ Checkpoints: enabled │ │ Apply Approval: required │ ╰───────────────────────────────────╯ ╭─ Created ─────────────────╮ │ Config: config.toml │ │ Database: cleveragents.db │ │ Logs: logs/ │ │ Cache: cache/ │ │ Backups: backups/ │ ╰───────────────────────────╯ ╭─ Schema ───────────────────────╮ │ Version: v3 │ │ Tables: 12 created │ │ Migrations: up to date │ ╰────────────────────────────────╯

✓ OK Environment initialized

agents session

Purpose Manage interactive sessions that hold a conversation history and orchestrator state.

agents session create

Purpose Create a new session for interactive work.

Arguments

--name NAME: Human-friendly session name.
--actor ACTOR: Orchestrator actor to use for session tell (defaults to configured default).
--metadata KEY=VALUE: Attach metadata to the session (repeatable).

Examples

$ agents session create --name weekly-planning --actor local/orchestrator --metadata team=platform ╭─ Session ──────────────────────╮ │ Name: weekly-planning │ │ ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z │ │ Actor: local/orchestrator │ │ Created: 2026-02-08 12:44 │ │ Namespace: local │ ╰────────────────────────────────╯ ╭─ Settings ─────────────╮ │ Automation: review │ │ Streaming: off │ │ Context: default │ │ Memory: enabled │ │ Max History: 50 turns │ ╰────────────────────────╯ ╭─ Actor Details ───────────────────╮ │ Provider: anthropic │ │ Model: claude-3.5 │ │ Temperature: 0.7 │ │ Context Window: 200K tokens │ ╰───────────────────────────────────╯ ╭─ Metadata ──────╮ │ - team=platform │ │ - quarter=Q1 │ ╰─────────────────╯

✓ OK Session created

agents session list

Purpose List sessions available on the local machine.

Arguments

--format table|json: Output format.

Examples

$ agents session list --format table ╭─ Sessions ───────────────────────────────────────────────────────────────────╮ │ ID Name Actor Messages Updated │ │ ──────── ─────────────── ────────────────── ──────── ──────────────── │ │ 01HXM2A6 weekly-planning local/orchestrator 6 2026-02-08 12:44 │ │ 01HXM1F2 refactor-sprint local/orchestrator 14 2026-02-07 18:11 │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Summary ────────────────────╮ │ Total: 2 │ │ Most Recent: weekly-planning │ │ Oldest: refactor-sprint │ │ Total Messages: 20 │ │ Storage: 42 KB │ ╰──────────────────────────────╯

✓ OK 2 sessions listed

agents session show

Purpose Show details and recent messages for a session.

Arguments

<SESSION_ID|NAME>: The session identifier or name.

Examples

$ agents session show weekly-planning ╭─ Session Summary ──────────────╮ │ Name: weekly-planning │ │ ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z │ │ Actor: local/orchestrator │ │ Messages: 6 │ │ Created: 2026-02-08 12:30 │ │ Updated: 2026-02-08 12:44 │ │ Automation: review │ ╰────────────────────────────────╯ ╭─ Recent Messages ──────────────────────────────────╮ │ user Create an action to refresh dependency locks │ │ assistant Plan created, running commands... │ │ assistant Completed 2 commands │ ╰────────────────────────────────────────────────────╯ ╭─ Linked Plans ──────────────────────────────╮ │ Plan ID Phase State │ │ ────────────────────────── ────── ──────── │ │ 01HXM8C2ZK4Q7C2B3F2R4VYV6J execute complete │ ╰─────────────────────────────────────────────╯ ╭─ Token Usage ──────────────╮ │ Input Tokens: 3,420 │ │ Output Tokens: 1,185 │ │ Estimated Cost: $0.0184 │ ╰────────────────────────────╯

✓ OK Session details loaded

agents session delete

Purpose Delete a session and its stored conversation history.

Arguments

<SESSION_ID|NAME>: The session identifier or name.
--yes: Skip the confirmation prompt.

Examples

$ agents session delete weekly-planning Delete session weekly-planning? [y/N]: y ╭─ Deletion Summary ─────────────╮ │ Session: weekly-planning │ │ ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z │ │ Messages: 6 removed │ │ Storage: 18 KB freed │ │ Plans Orphaned: 0 │ ╰────────────────────────────────╯ ╭─ Cleanup ───────────╮ │ Backups: none │ │ Logs: preserved │ │ Context: cleared │ │ Checkpoints: none │ ╰─────────────────────╯

✓ OK Session deleted

agents session export

Purpose Export a session as a portable JSON file.

Arguments

<SESSION_ID|NAME>: The session identifier or name.
--output FILE: Output file path.

Examples

$ agents session export weekly-planning --output /tmp/weekly-planning.json ╭─ Session Export ──────────────────╮ │ Session: weekly-planning │ │ Output: /tmp/weekly-planning.json │ │ Messages: 6 │ │ Size: 24 KB │ │ Format: JSON │ ╰───────────────────────────────────╯ ╭─ Contents ─────────────────╮ │ Messages: 6 │ │ Plan References: 1 │ │ Metadata Keys: 2 │ │ Actor Config: included │ │ Schema Version: v3 │ ╰────────────────────────────╯ ╭─ Integrity ──────────────────╮ │ Checksum: sha256:7a9b...42c1 │ │ Encrypted: no │ ╰──────────────────────────────╯

✓ OK Export completed

agents session import

Purpose Import a session JSON file.

Arguments

--input FILE: Input JSON file.
--name NAME: Optional override for the session name.

Examples


$ agents session import --input /tmp/weekly-planning.json --name weekly-planning-restored
╭─ Session Import ───────────────────────╮
│ Input: /tmp/weekly-planning.json       │
│ Name: weekly-planning-restored         │
│ Session ID: 01HXM3D3B2W4CQYQ3P4ZB8A5T1 │
│ Messages: 6                            │
│ Schema: v3                              │
╰────────────────────────────────────────╯
╭─ Validation ────────────╮
│ Checksum: verified     │
│ Schema: compatible     │
│ Actor Ref: resolved    │
╰─────────────────────────╯
╭─ Merge ──────────────╮
│ Existing: none       │
│ Strategy: create new │
╰──────────────────────╯
✓ OK Import completed

agents session tell

Purpose Send a natural-language request to the orchestrator. The orchestrator can create actions, plans, or project changes by issuing the necessary CleverAgents commands under the hood.

Arguments

"<prompt>": Instruction text.
--session SESSION_ID|NAME: Session to use (defaults to the most recent session).
--actor ACTOR: Override the session actor for this request.
--stream: Stream progress as the orchestrator works.

Examples

$ agents session tell "Create an action to refresh dependency locks and add it to the platform project" \ --session weekly-planning ╭─ Plan Request ──────────────────────────────────────────╮ │ Actor: local/orchestrator │ │ Session: weekly-planning │ │ Automation: review │ │ Prompt: Create an action to refresh dependency locks... │ ╰─────────────────────────────────────────────────────────╯ ╭─ Commands Executed ────────────────────────────────────────────────────────────────────────────────────────╮ │ - agents action create local/refresh-locks --strategy-actor local/planner --execution-actor local/executor │ │ - agents resource add git-checkout local/platform-repo --path /repos/platform │ │ - agents project link-resource --project local/platform --resource local/platform-repo │ ╰────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ ╭─ Result ────────────────────────────╮ │ Action: local/refresh-locks (draft) │ │ Project: local/platform │ │ Resource: repo │ ╰─────────────────────────────────────╯ ╭─ Usage ─────────────────────╮ │ Input Tokens: 1,842 │ │ Output Tokens: 624 │ │ Cost: $0.0094 │ │ Duration: 3.2s │ │ Tool Calls: 2 │ ╰─────────────────────────────╯

✓ OK Orchestrator completed 2 commands

agents project

Purpose Manage projects and their resources.

agents project create

Purpose Create a new project record.

Arguments

--name/-n NAME: Namespaced project name.
--description/-d TEXT: Optional description.
--invariant TEXT: Invariant to attach to this project (repeatable). These invariants apply to all plans targeting this project.
--invariant-actor ACTOR: Invariant Reconciliation Actor for this project. Used to reconcile project-level invariants against global invariants for all plans targeting this project (unless the plan overrides it).

Examples

$ agents project create --name local/api-service --description "Backend API" ╭─ Project ──────────────────────╮ │ Name: local/api-service │ │ ID: 01HXM4T08Y0N5R9VZ4QX4BPTZ1 │ │ Description: Backend API │ │ Type: local │ │ Created: 2026-02-08 12:46 │ ╰────────────────────────────────╯ ╭─ Paths ────────────────────────────────────╮ │ Root: /repos/api-service │ │ Data Dir: /repos/api-service/.cleveragents │ ╰────────────────────────────────────────────╯ ╭─ Defaults ────────────────────╮ │ Sandbox: git_worktree │ │ Validation: unset │ │ Context Filters: none │ │ Automation: (inherits global) │ │ Apply Approval: required │ ╰───────────────────────────────╯ ╭─ Resources ──────╮ │ Total: 0 │ │ Indexed: 0 │ │ Sandboxable: 0 │ ╰──────────────────╯

✓ OK Project created

agents project link-resource

Purpose Link a registered resource to a project. The resource must already be registered via agents resource add. A resource can be linked to multiple projects. Optionally, the resource can be marked as read-only within this project context, and given an alias for convenience.

Arguments

--project/-p PROJECT: Project name.
--resource/-r RESOURCE: Registered resource name.
--read-only: Mark the resource as read-only within this project (even if the resource itself is writable).
--alias ALIAS: Optional short alias for referencing this resource within the project.

Examples

$ agents resource add git-checkout local/api-repo --path /repos/api --branch main $ agents project link-resource --project local/api-service --resource local/api-repo ╭─ Resource Linked ──────────────────────╮ │ Project: local/api-service │ │ Resource: local/api-repo │ │ Type: git-checkout │ │ Read-Only: no │ │ Alias: (none) │ ╰────────────────────────────────────────╯ ╭─ Permissions ────────────╮ │ Read: allowed │ │ Write: allowed │ │ Apply: requires approval │ ╰──────────────────────────╯ ╭─ Indexing ─────────────────────╮ │ Status: indexing... │ │ Files Found: 347 │ │ Language: Python (primary) │ │ Estimated Time: ~20 seconds │ ╰────────────────────────────────╯

✓ OK Resource linked to project

agents project unlink-resource

Purpose Unlink a resource from a project. The resource itself remains registered in the Resource Registry and can still be linked to other projects. Active plans using this resource in this project context will be warned.

Arguments

--project/-p PROJECT: Project name.
--resource/-r RESOURCE: Resource name.
--yes: Skip confirmation prompt.

Examples

$ agents project unlink-resource --project local/api-service --resource local/api-repo Unlink local/api-repo from local/api-service? [y/N]: y ╭─ Resource Unlinked ────────────────────╮ │ Project: local/api-service │ │ Resource: local/api-repo │ │ Type: git-checkout │ ╰────────────────────────────────────────╯ ╭─ Index Cleanup ──────────╮ │ Text Index: 347 removed │ │ Vectors: 892 removed │ │ Graph Triples: cleared │ │ Duration: 0.3s │ ╰──────────────────────────╯ ╭─ Project Summary ──────────────╮ │ Linked Resources: 1 remaining │ │ Last Updated: 2026-02-09 10:30 │ │ Active Plans: 0 │ ╰────────────────────────────────╯

✓ OK Resource unlinked from project

agents project list

Purpose List projects with optional filters.

Arguments

--namespace/-n NS: Filter by namespace.
--format table|json: Output format.

Examples

$ agents project list --format table ╭─ Projects ────────────────────────────────────────────────────────╮ │ ID Name Resources Remote Active Plans │ │ ──────── ───────────────── ───────── ────── ──────────── │ │ 01HXM4T0 local/api-service 2 No 1 │ │ 01HXM4B9 local/docs 1 No 0 │ ╰───────────────────────────────────────────────────────────────────╯ ╭─ Summary ──────────────────╮ │ Total: 2 │ │ With Resources: 2 │ │ Remote: 0 │ │ Total Resources: 3 │ │ Indexed Files: 1,247 │ │ Active Plans: 1 │ ╰────────────────────────────╯

✓ OK 2 projects listed

agents project show

Purpose Show full project details.

Arguments

<NAME>: Project name.
--format rich|json: Output format.

Examples

$ agents project show local/api-service ╭─ Project Details ──────────────╮ │ Name: local/api-service │ │ ID: 01HXM4T08Y0N5R9VZ4QX4BPTZ1 │ │ Description: Backend API │ │ Resources: 2 │ │ Remote: no │ │ Created: 2026-02-08 12:46 │ ╰────────────────────────────────╯ ╭─ Linked Resources ──────────────────────────────────────────────────────╮ │ Resource Type Sandbox Read-Only │ │ ──────────────── ────────────── ──────────────────── ───────── │ │ local/api-repo git-checkout git_worktree no │ │ local/staging-db local/database transaction_rollback yes │ ╰─────────────────────────────────────────────────────────────────────────╯ ╭─ Validation ────────╮ │ Test: pytest │ │ Lint: ruff check . │ │ Type Check: pyright │ │ Build: (none) │ │ Timeout: 300s │ ╰─────────────────────╯ ╭─ Context ───────────────────╮ │ Include: repo │ │ Exclude: /node_modules/ │ │ Max File Size: 1 MB │ ╰─────────────────────────────╯ ╭─ Indexing Status ──────────╮ │ Text Index: ready │ │ Vector Index: ready │ │ Graph Store: disabled │ │ Indexed Files: 347 │ │ Last Indexed: 12:48 │ ╰────────────────────────────╯ ╭─ Active Plans ──────────────────────────╮ │ Plan ID Action Phase │ │ ──────── ─────────────────── ─────── │ │ 01HXM7A9 local/code-coverage execute │ ╰─────────────────────────────────────────╯

✓ OK Project loaded

agents project set-validation

Purpose Set or update validation commands for a project or a specific resource.

Arguments

--project/-p PROJECT: Project name.
--resource NAME: Optional resource name.
--test-command CMD: Test command.
--lint-command CMD: Lint command.
--type-check-command CMD: Type-check command.
--build-command CMD: Build command.
--timeout SECONDS: Timeout per command.
--clear: Clear validation config.

Examples

$ agents project set-validation --project local/api-service --resource repo \ --test-command "pytest" --lint-command "ruff check ." --type-check-command "pyright" ╭─ Validation Commands ╮ │ Test: pytest │ │ Lint: ruff check . │ │ Type Check: pyright │ │ Build: (none) │ │ Timeout: 300s │ ╰──────────────────────╯ ╭─ Scope ─────────────────────╮ │ Project: local/api-service │ │ Resource: repo │ │ Applies To: sandbox + apply │ ╰─────────────────────────────╯ ╭─ Execution Order ─────────────────╮ │ 1. Type Check → pyright │ │ 2. Lint → ruff check . │ │ 3. Test → pytest │ │ On Failure: iterate up to 3 tries │ │ Then: escalate to user │ ╰───────────────────────────────────╯ ╭─ Notes ──────────────────────╮ │ - Commands run after Execute │ │ - Failures block Apply phase │ │ - Actor can auto-fix issues │ ╰──────────────────────────────╯

✓ OK Validation updated

agents project delete

Purpose Delete a project and all associated resources.

Arguments

<NAME>: Project name.
--force/-f: Delete even if active plans exist.
--yes: Skip confirmation prompt.

Examples

$ agents project delete local/docs Delete project local/docs? This cannot be undone. [y/N]: y ╭─ Deletion Summary ──────────────────╮ │ Project: local/docs │ │ ID: 01HXM4B9F2C1V8X2N6Q7K9L0M1 │ │ Resources: 1 removed │ │ Data Dir: /repos/docs/.cleveragents │ ╰─────────────────────────────────────╯ ╭─ Index Cleanup ────────╮ │ Text Index: cleared │ │ Vectors: 240 removed │ │ Graph Triples: none │ │ Storage Freed: 12 MB │ ╰────────────────────────╯ ╭─ Backups ────────────────────────────────────╮ │ Snapshot: /backups/local-docs-2026-02-08.tgz │ │ Retention: 7 days │ ╰──────────────────────────────────────────────╯

✓ OK Project deleted

agents project context

Purpose Manage context policies for the hot/warm/cold tiers and per-view context selection.

agents project context set

Purpose Set the context policy for a project and (optionally) a specific view.

Arguments

--project PROJECT: Project name.
--view strategize|execute|apply|default: Which view this policy applies to.
--include-resource NAME: Resource allowlist (repeatable).
--exclude-resource NAME: Resource denylist (repeatable).
--include-path GLOB: Path allowlist (repeatable).
--exclude-path GLOB: Path denylist (repeatable).
--hot-max-tokens N: Maximum token budget for hot context. This is a soft cap and may be null. The actor/LLM hard limit can be lower; the effective hot context is the lesser of the two.
--warm-max-decisions N: Maximum number of decisions kept in warm context.
--cold-max-decisions N: Maximum number of decisions kept in cold context.
--query-limit N: Max number of retrieval results per query.
--max-file-size BYTES: Max file size included in context.
--max-total-size BYTES: Max total size across included files.
--summarize/--no-summarize: Enable or disable summarization for large context segments.
--summary-max-tokens N: Token limit for generated summaries.
--clear: Clear the policy for the selected view.

Examples

$ agents project context set --project local/api-service --view strategize \ --include-resource repo --exclude-path "**/node_modules/**" \ --hot-max-tokens 12000 --warm-max-decisions 50 --cold-max-decisions 200 \ --summarize --summary-max-tokens 800 ╭─ Context Policy ────────────╮ │ Project: local/api-service │ │ View: strategize │ │ Include: repo │ │ Exclude: /node_modules/ │ ╰─────────────────────────────╯ ╭─ Limits ─────────────────────╮ │ Hot Tokens: 12000 (soft cap) │ │ Warm Decisions: 50 │ │ Cold Decisions: 200 │ │ Query Limit: 20 │ │ Max File Size: 1 MB │ │ Max Total Size: 50 MB │ ╰──────────────────────────────╯ ╭─ Summarization ─╮ │ Enabled: yes │ │ Max Tokens: 800 │ ╰─────────────────╯ ╭─ Other Views ────────╮ │ execute: (default) │ │ apply: (default) │ │ default: (unset) │ ╰──────────────────────╯

✓ OK Context policy updated

agents project context show

Purpose Show the active context policy for a project.

Arguments

--project PROJECT: Project name.
--view strategize|execute|apply|default: View to display.
--format table|json: Output format.

Examples

$ agents project context show --project local/api-service --view strategize ╭─ Context Policy ────────────╮ │ Project: local/api-service │ │ View: strategize │ │ Include: repo │ │ Exclude: /node_modules/ │ ╰─────────────────────────────╯ ╭─ Limits ─────────────────────╮ │ Hot Tokens: 12000 (soft cap) │ │ Warm Decisions: 50 │ │ Cold Decisions: 200 │ │ Query Limit: 20 │ │ Max File Size: 1 MB │ │ Max Total Size: 50 MB │ ╰──────────────────────────────╯ ╭─ Summarization ─╮ │ Enabled: yes │ │ Max Tokens: 800 │ ╰─────────────────╯ ╭─ Current Usage ──────────────╮ │ Hot Context: 8,420 / 12,000 │ │ Warm Entries: 12 / 50 │ │ Cold Entries: 47 / 200 │ │ Indexed Resources: 1 │ ╰──────────────────────────────╯

✓ OK Context policy loaded

agents actor

Purpose Manage actors and run actor configurations directly.

agents actor run

Purpose Run an actor configuration in isolation with simple, manual context.

Arguments

--config/-c FILE...: YAML or JSON config files.
--prompt/-p TEXT: Prompt to send.
--output/-o FILE: Output file path.
--verbose/-v: Increase verbosity (repeatable).
--unsafe/-u: Allow unsafe configs.
--context NAME: Named actor context to attach.
--context-dir PATH: Context storage location.
--load-context FILE: Load context from JSON.
--temperature/-t FLOAT: Override temperature.
--allow-rxpy-in-run-mode: Allow RxPy routes in run mode.

Examples

$ agents actor run -c ./actors/code_reader.yaml -p "Summarize the README" --context docs ╭─ Run Summary ─────────────────────╮ │ Actor: local/code_reader │ │ Context: docs │ │ Config: ./actors/code_reader.yaml │ │ Temperature: 0.2 │ │ Provider: anthropic │ │ Model: claude-3.5 │ ╰───────────────────────────────────╯ ╭─ Inputs ─────────────────────╮ │ Prompt: Summarize the README │ │ Context Files: 3 │ │ Context Size: 12.4 KB │ ╰──────────────────────────────╯ ╭─ Result Metrics ──────╮ │ Output: stdout │ │ Input Tokens: 1,524 │ │ Output Tokens: 842 │ │ Duration: 1.8s │ │ Cost: $0.0021 │ │ Tool Calls: 0 │ ╰───────────────────────╯

✓ OK Summary generated

agents actor add

Purpose Add a new actor configuration.

Arguments

<NAME>: Actor name.
--config/-c FILE: Actor config file.
--unsafe: Mark actor as unsafe.
--set-default: Set as default actor.
--option/-o key=value: Option override (repeatable).

Examples

$ agents actor add local/reviewer --config ./actors/reviewer.yaml --set-default ╭─ Actor Added ────────╮ │ Name: local/reviewer │ │ Provider: openai │ │ Model: gpt-4 │ │ Default: yes │ │ Unsafe: no │ │ Type: graph │ ╰──────────────────────╯ ╭─ Config ─────────────────────╮ │ Path: ./actors/reviewer.yaml │ │ Hash: 8b3f3d2 │ │ Options: 4 │ │ Nodes: 3 │ │ Edges: 4 │ ╰──────────────────────────────╯ ╭─ Capabilities ───────╮ │ - code review │ │ - diff summarization │ │ - lint guidance │ ╰──────────────────────╯ ╭─ Tools ────────────────────────╮ │ Tool Read-Only Safe │ │ ──────────── ───────── ──── │ │ read_file yes yes │ │ search_files yes yes │ │ git_diff yes yes │ ╰────────────────────────────────╯

✓ OK Actor added

agents actor update

Purpose Update an existing actor configuration.

Arguments

<NAME>: Actor name.
--config/-c FILE: Updated config file.
--unsafe: Mark actor as unsafe.
--safe: Mark actor as safe.
--set-default: Set as default actor.
--option/-o key=value: Option override (repeatable).

Examples

$ agents actor update local/reviewer --option temperature=0.2 ╭─ Actor Updated ───────────╮ │ Name: local/reviewer │ │ Change: temperature → 0.2 │ │ Updated: 2026-02-08 13:02 │ │ Config Hash: 9c4e2a1 │ ╰───────────────────────────╯ ╭─ Effective Options ╮ │ - temperature: 0.2 │ │ - max_tokens: 2048 │ │ - top_p: 1.0 │ ╰────────────────────╯ ╭─ Previous Value ───────╮ │ temperature: 0.7 → 0.2 │ ╰────────────────────────╯

✓ OK Actor updated

agents actor remove

Purpose Remove a custom actor.

Arguments

<NAME>: Actor name.

Examples

$ agents actor remove local/reviewer ╭─ Actor Removed ──────╮ │ Name: local/reviewer │ │ Provider: openai │ │ Model: gpt-4 │ ╰──────────────────────╯ ╭─ Impact ───────────────────────────────────╮ │ Default Actor: reset to local/orchestrator │ │ Sessions: 0 affected │ │ Active Plans: 0 affected │ │ Actions Referencing: 0 │ ╰────────────────────────────────────────────╯ ╭─ Cleanup ──────────────╮ │ Config: kept on disk │ │ Contexts: 1 orphaned │ ╰────────────────────────╯

✓ OK Actor removed

agents actor list

Purpose List all actors.

Arguments

None.

Examples

$ agents actor list ╭─ Actors ──────────────────────────────────────────────────────────────╮ │ Name Provider Model Default Built-in Unsafe │ │ ────────────── ───────── ────────── ─────── ──────── ────── │ │ local/reviewer openai gpt-4 ✓ no │ │ openai/gpt-4 openai gpt-4 ✓ no │ │ anthropic/3.5 anthropic claude-3.5 ✓ no │ ╰──────────────────────────────────────────────────────────────────────╯ ╭─ Summary ──────────────╮ │ Total: 3 │ │ Built-in: 2 │ │ Custom: 1 │ │ Unsafe: 0 │ │ Providers Used: 2 │ ╰────────────────────────╯

✓ OK 3 actors listed

agents actor show

Purpose Show details for a single actor.

Arguments

<NAME>: Actor name.

Examples

$ agents actor show local/reviewer ╭─ Actor Details ────────────────────╮ │ Name: local/reviewer │ │ Provider: openai │ │ Model: gpt-4 │ │ Default: yes │ │ Built-in: no │ │ Unsafe: no │ │ Type: graph │ │ Created: 2026-02-08 12:35 │ │ Updated: 2026-02-08 12:40 │ │ Config: ./actors/reviewer.yaml │ │ Config Hash: 9c4e2a1 │ ╰────────────────────────────────────╯ ╭─ Options ──────────╮ │ - temperature: 0.2 │ │ - max_tokens: 2048 │ │ - top_p: 1.0 │ ╰────────────────────╯ ╭─ Graph Structure ─╮ │ Nodes: 3 │ │ Edges: 4 │ │ Entry: analyze │ │ Exit: report │ ╰───────────────────╯ ╭─ Tools ────────────────────────╮ │ Tool Read-Only Safe │ │ ──────────── ───────── ──── │ │ read_file yes yes │ │ search_files yes yes │ │ git_diff yes yes │ ╰────────────────────────────────╯ ╭─ Permissions ───────╮ │ Unsafe: no │ │ Filesystem: allowed │ │ Network: restricted │ ╰─────────────────────╯ ╭─ Usage ─────────────────────────────────────────╮ │ Referenced by Actions: 1 (local/code-coverage) │ │ Active in Sessions: 0 │ │ Total Runs: 14 │ │ Avg Cost/Run: $0.0032 │ ╰─────────────────────────────────────────────────╯

✓ OK Actor loaded

agents actor set-default

Purpose Set the default actor.

Arguments

<NAME>: Actor name.

Examples

$ agents actor set-default local/reviewer ╭─ Default Actor ──────────────╮ │ Current: local/reviewer │ │ Previous: local/orchestrator │ │ Provider: openai │ │ Model: gpt-4 │ ╰──────────────────────────────╯ ╭─ Impact ──────────────────────────────────╮ │ Sessions: new sessions use local/reviewer │ │ Existing Sessions: unchanged │ │ Active Plans: unchanged │ ╰───────────────────────────────────────────╯ ╭─ Saved To ──────────────────────────╮ │ File: ~/.cleveragents/config.toml │ │ Key: default-actor │ ╰─────────────────────────────────────╯

✓ OK Default actor updated

agents actor context

Purpose Manage manual context for actor runs. These commands mirror the legacy context behavior but are scoped to an actor context name.

agents actor context add

Purpose Add files or directories to an actor context.

Arguments

--name NAME: Context name.
<PATHS...>: Files or directories to add.
-r/--recursive: Add directories recursively.

Examples

$ agents actor context add --name docs README.md docs/ ╭─ Context Files Added ╮ │ Context: docs │ │ Added: 12 items │ │ Total: 12 items │ │ Total Size: 52 KB │ ╰──────────────────────╯ ╭─ Added Items ───────────╮ │ Name Type Size │ │ ───────── ──── ────── │ │ README.md file 4.2 KB │ │ docs/ dir 48 KB │ ╰─────────────────────────╯ ╭─ Limits ────────╮ │ Max Files: 500 │ │ Max Size: 25 MB │ │ Used: 0.2% │ ╰─────────────────╯ ╭─ Skipped ─────────────────────────╮ │ Binary Files: 2 (not text) │ │ Over Size Limit: 0 │ ╰───────────────────────────────────╯

✓ OK Context updated

agents actor context load

Purpose Alias for context add.

Arguments

Same as context add.

Examples

$ agents actor context load --name docs README.md ╭─ Context Files Added ╮ │ Context: docs │ │ Added: 1 item │ │ Total: 13 items │ ╰──────────────────────╯ ╭─ Recent Item ───╮ │ Name: README.md │ │ Size: 4.2 KB │ ╰─────────────────╯

✓ OK Context updated

agents actor context rm

Purpose Remove files or directories from an actor context.

Arguments

--name NAME: Context name.
<PATHS...>: Paths to remove.

Examples

$ agents actor context rm --name docs README.md ╭─ Context Files Removed ╮ │ Context: docs │ │ Removed: README.md │ │ Total: 12 items │ ╰────────────────────────╯ ╭─ Stats ───────────────────╮ │ Remaining Size: 48 KB │ │ Updated: 2026-02-08 13:06 │ ╰───────────────────────────╯

✓ OK Context updated

agents actor context list

Purpose List files stored in an actor context.

Arguments

[NAME]: Context name (optional to list all contexts).
--format table|json: Output format.

Examples

$ agents actor context list docs ╭─ Context Files ──────────────────────────────╮ │ Name Type Size Added │ │ ──────────────── ──── ─────── ────────── │ │ README.md file 4.2 KB 02-08 12:10 │ │ docs/overview.md file 12.8 KB 02-08 12:10 │ │ docs/cli.md file 9.5 KB 02-08 12:10 │ ╰──────────────────────────────────────────────╯ ╭─ Stats ───────────────────────╮ │ Total Files: 3 │ │ Total Size: 26.5 KB │ │ Estimated Tokens: ~6,600 │ │ Languages: Markdown │ ╰───────────────────────────────╯

✓ OK 3 files listed

agents actor context show

Purpose Show content of a file in an actor context.

Arguments

--name NAME: Context name.
[PATH]: File path (optional for summary).

Examples

$ agents actor context show --name docs README.md ╭─ Metadata ──────────────────╮ │ Path: README.md │ │ Size: 4.2 KB │ │ Added: 2026-02-08 12:10 │ │ Language: Markdown │ │ Estimated Tokens: ~1,050 │ │ Lines: 87 │ ╰────────────────────────────╯ ╭─ Preview ─────────────────────────────────────────╮ │ # CleverAgents │ │ │ │ CleverAgents is your command center for agents... │ │ ... │ ╰───────────────────────────────────────────────────╯

✓ OK Content displayed

agents actor context export

Purpose Export a context as JSON.

Arguments

--name NAME: Context name.
--output FILE: Output file path.

Examples

$ agents actor context export --name docs --output /tmp/docs-context.json ╭─ Context Export ───────────────╮ │ Context: docs │ │ Output: /tmp/docs-context.json │ │ Items: 12 │ │ Size: 48 KB │ ╰────────────────────────────────╯ ╭─ Integrity ──────────────────╮ │ Checksum: sha256:19b2...a7d0 │ │ Compressed: no │ ╰──────────────────────────────╯

✓ OK Export completed

agents actor context import

Purpose Import a context from JSON.

Arguments

--name NAME: Context name.
--input FILE: Input JSON file.

Examples


$ agents actor context import --name docs --input /tmp/docs-context.json
╭─ Context Import ──────────────╮
│ Context: docs                 │
│ Input: /tmp/docs-context.json │
│ Items: 12                     │
╰───────────────────────────────╯
╭─ Merge ───────────╮
│ Strategy: replace │
│ Conflicts: 0      │
╰───────────────────╯
✓ OK Import completed

agents actor context delete

Purpose Delete an entire context.

Arguments

--name NAME: Context name.
--yes: Skip confirmation.

Examples

$ agents actor context delete --name docs Delete context docs? [y/N]: y ╭─ Context Deleted ────╮ │ Context: docs │ │ Items: 12 removed │ │ Storage: 48 KB freed │ ╰──────────────────────╯ ╭─ Cleanup ───────╮ │ Backups: none │ │ Logs: preserved │ ╰─────────────────╯

✓ OK Context deleted

agents actor context clear

Purpose Clear all files from a context but keep the context itself.

Arguments

--name NAME: Context name.
--yes: Skip confirmation.

Examples

$ agents actor context clear --name docs Clear context docs? [y/N]: y ╭─ Context Cleared ────╮ │ Context: docs │ │ Items: 12 removed │ │ Storage: 48 KB freed │ ╰──────────────────────╯ ╭─ Retention ────────╮ │ Context: preserved │ │ Files: removed │ ╰────────────────────╯

✓ OK Context cleared

agents skill

Purpose Manage skills — reusable, namespaced collections of tools. Skills are defined in their own YAML configuration files and registered in the system through these commands. Once registered, skills can be referenced by actors.

agents skill add

Purpose Register a new skill from a YAML configuration file. If a skill with the same name already exists, the command fails unless the --upgrade flag is provided, which allows overwriting the existing registration with the new configuration.

Arguments

<NAME>: Namespaced skill name.
--config/-c FILE: Path to the skill YAML configuration file.
--description/-d TEXT: Optional description override (overrides what's in the YAML).
--upgrade: Allow overwriting an existing skill registration. Without this flag, attempting to add a skill whose name is already registered will fail.

Examples

Registering a new skill:

$ agents skill add local/devops-toolkit --config ./skills/devops-toolkit.yaml ╭─ Skill Registered ──────────────────────╮ │ Name: local/devops-toolkit │ │ ID: 01HXMC4T08Y0N5R9VZ4QX4BPTZ1 │ │ Description: Full-stack development tools │ │ Config: ./skills/devops-toolkit.yaml │ │ Created: 2026-02-08 13:10 │ ╰─────────────────────────────────────────╯ ╭─ Includes ────────────────────╮ │ local/file-ops (registered) │ │ local/git-ops (registered) │ │ local/github (registered) │ ╰───────────────────────────────╯ ╭─ Tool Sources ─────────────────────────────╮ │ Source Count Details │ │ ───────────── ───── ─────────────────── │ │ builtin 16 file, dir, search, git │ │ mcp 4 github (4 tools) │ │ agent_skill 2 deploy, code-review │ │ custom 1 run_migrations │ │ ───────────── ───── ─────────────────── │ │ Total: 23 │ ╰────────────────────────────────────────────╯ ╭─ MCP Servers ────────────────────╮ │ linear: validated (4 tools) │ ╰──────────────────────────────────╯

✓ OK Skill registered with 23 tools

Attempting to add a skill that already exists (without --upgrade):

$ agents skill add local/devops-toolkit --config ./skills/devops-toolkit-v2.yaml ✗ Error: Skill 'local/devops-toolkit' is already registered. To overwrite the existing configuration, re-run with --upgrade:

agents skill add local/devops-toolkit --config ./skills/devops-toolkit-v2.yaml --upgrade

Upgrading an existing skill with --upgrade:

$ agents skill add local/devops-toolkit --config ./skills/devops-toolkit-v2.yaml --upgrade ╭─ Skill Upgraded ─────────────────────────╮ │ Name: local/devops-toolkit │ │ Description: Full-stack development tools │ │ Upgraded: 2026-02-08 14:22 │ ╰─────────────────────────────────────────╯ ╭─ Changes ─────────────────────╮ │ Tools Added: 2 │ │ Tools Removed: 0 │ │ Tools Modified: 1 │ │ Includes Changed: no │ │ MCP Servers Changed: no │ ╰───────────────────────────────╯ ╭─ Affected Actors ────────────────────────────╮ │ Warning: 2 actors reference this skill: │ │ - local/code-assistant │ │ - local/full-stack-assistant │ │ These actors will pick up changes on next use │ ╰──────────────────────────────────────────────╯

✓ OK Skill upgraded (23 → 25 tools)

agents skill remove

Purpose Remove a registered skill.

Arguments

<NAME>: Skill name to remove.
--yes: Skip confirmation prompt.

Examples

$ agents skill remove local/devops-toolkit Remove skill local/devops-toolkit? [y/N]: y ╭─ Skill Removed ──────────────────────╮ │ Name: local/devops-toolkit │ │ Tools: 23 removed from registry │ │ MCP Servers: 1 connection closed │ ╰──────────────────────────────────────╯ ╭─ Dependency Check ───────────────────────────────╮ │ Warning: 1 skill includes this skill: │ │ - local/full-stack-dev (will lose devops tools) │ │ Warning: 2 actors reference this skill: │ │ - local/code-assistant │ │ - local/full-stack-assistant │ ╰──────────────────────────────────────────────────╯

✓ OK Skill removed

agents skill list

Purpose List registered skills with optional filters.

Arguments

--namespace/-n NS: Filter by namespace.
--source SOURCE: Filter by tool source type (mcp, agent_skill, builtin, custom).
--format table|json: Output format.

Examples

$ agents skill list --format table ╭─ Skills ────────────────────────────────────────────────────────────╮ │ Name Tools Includes Sources │ │ ────────────────────── ───── ──────── ────────────────────── │ │ local/file-ops 9 0 builtin │ │ local/git-ops 4 0 builtin │ │ local/github 4 0 mcp │ │ local/devops-toolkit 23 3 builtin, mcp, custom │ │ local/full-stack-dev 28 4 builtin, mcp, custom │ ╰─────────────────────────────────────────────────────────────────────╯ ╭─ Summary ─────────╮ │ Total: 5 │ │ Local: 5 │ │ Server: 0 │ │ Total Tools: 28 │ ╰───────────────────╯

✓ OK 5 skills listed

agents skill show

Purpose Show full details for a registered skill, including its includes, tool sources, and capability summary.

Arguments

<NAME>: Skill name.
--format rich|json: Output format.

Examples

$ agents skill show local/devops-toolkit ╭─ Skill Details ─────────────────────────────╮ │ Name: local/devops-toolkit │ │ ID: 01HXMC4T08Y0N5R9VZ4QX4BPTZ1 │ │ Description: Full-stack development tools │ │ Config: ./skills/devops-toolkit.yaml │ │ Created: 2026-02-08 13:10 │ │ Updated: 2026-02-08 14:22 │ ╰─────────────────────────────────────────────╯ ╭─ Includes (3) ────────────────────────────╮ │ local/file-ops → 9 tools (builtin) │ │ local/git-ops → 4 tools (builtin) │ │ local/github → 4 tools (mcp) │ ╰───────────────────────────────────────────╯ ╭─ Direct Tools (6) ────────────────────────────────────────╮ │ Name Source Writes Checkpoint │ │ ──────────────── ─────────── ────── ────────── │ │ create_issue mcp:linear yes no │ │ list_issues mcp:linear no — │ │ deploy-to-staging agent_skill yes composite │ │ code-review agent_skill no — │ │ run_migrations custom yes transaction │ │ shell_execute builtin yes snapshot │ ╰───────────────────────────────────────────────────────────╯ ╭─ MCP Servers (1) ───────────────────╮ │ linear: stdio, 2 tools, connected │ ╰─────────────────────────────────────╯ ╭─ Capability Summary ──────────╮ │ Total Tools: 23 │ │ Read-Only: 14 │ │ Writes: 9 │ │ Checkpointable: 17 │ │ Has Side Effects: 3 │ │ Requires Approval: 1 │ ╰───────────────────────────────╯ ╭─ Referenced By ───────────────────╮ │ Actors: local/code-assistant │ │ Skills: local/full-stack-dev │ ╰───────────────────────────────────╯

✓ OK Skill loaded

agents skill tools

Purpose List all tools provided by a skill, including those inherited from included skills (the flattened tool set).

Arguments

<NAME>: Skill name.
--format table|json: Output format.

Examples

$ agents skill tools local/devops-toolkit ╭─ Tools for local/devops-toolkit ─────────────────────────────────────────────────────────╮ │ Tool Source From Skill Read-Only Writes Checkpoint │ │ ───────────────── ─────────── ────────────── ───────── ────── ────────── │ │ read_file builtin local/file-ops ✓ — — │ │ write_file builtin local/file-ops — ✓ file │ │ edit_file builtin local/file-ops — ✓ file │ │ delete_file builtin local/file-ops — ✓ file │ │ move_file builtin local/file-ops — ✓ file │ │ copy_file builtin local/file-ops — ✓ file │ │ create_directory builtin local/file-ops — ✓ file │ │ list_directory builtin local/file-ops ✓ — — │ │ delete_directory builtin local/file-ops — ✓ file │ │ search_files builtin local/file-ops ✓ — — │ │ find_definition builtin local/file-ops ✓ — — │ │ find_references builtin local/file-ops ✓ — — │ │ git_status builtin local/git-ops ✓ — — │ │ git_diff builtin local/git-ops ✓ — — │ │ git_log builtin local/git-ops ✓ — — │ │ git_blame builtin local/git-ops ✓ — — │ │ create_issue mcp:github local/github — ✓ no │ │ create_pr mcp:github local/github — ✓ no │ │ list_repos mcp:github local/github ✓ — — │ │ get_file_contents mcp:github local/github ✓ — — │ │ create_issue mcp:linear (direct) — ✓ no │ │ list_issues mcp:linear (direct) ✓ — — │ │ run_migrations custom (direct) — ✓ transaction │ ╰──────────────────────────────────────────────────────────────────────────────────────────╯ ╭─ Summary ──────────────────╮ │ Total: 23 │ │ From Includes: 17 │ │ Direct: 6 │ │ Read-Only: 14 │ │ Writes: 9 │ │ Checkpointable: 17 │ ╰────────────────────────────╯

✓ OK 23 tools listed

agents tool

Purpose Manage tools — namespaced, independently registered, callable operations. Tools are defined in their own YAML configuration files and registered in the system through these commands. Once registered, tools can be referenced by name in skills (as part of a tool collection) and in actor graphs (as tool nodes).

agents tool add

Purpose Register a new tool from a YAML configuration file. If a tool with the same name already exists, the command fails unless the --upgrade flag is provided, which allows overwriting the existing registration with the new configuration.

Arguments

<NAME>: Namespaced tool name.
--config/-c FILE: Path to the tool YAML configuration file.
--description/-d TEXT: Optional description override (overrides what's in the YAML).
--upgrade: Allow overwriting an existing tool registration. Without this flag, attempting to add a tool whose name is already registered will fail.

Examples

Registering a new tool:

$ agents tool add local/run-migrations --config ./tools/run-migrations.yaml ╭─ Tool Registered ───────────────────────────╮ │ Name: local/run-migrations │ │ ID: 01HXMC5T09Z1N6S0WZ5RY5CQUZ2 │ │ Description: Run database migrations │ │ Source: custom │ │ Config: ./tools/run-migrations.yaml │ │ Created: 2026-02-09 10:15 │ ╰─────────────────────────────────────────────╯ ╭─ Capability ──────────────────╮ │ Writes: true │ │ Write Scope: database:migrations │ │ Checkpointable: true │ │ Checkpoint Scope: transaction │ │ Side Effects: schema_mutation │ ╰───────────────────────────────╯

✓ OK Tool registered

Attempting to add a tool that already exists (without --upgrade):

$ agents tool add local/run-migrations --config ./tools/run-migrations-v2.yaml ✗ Error: Tool 'local/run-migrations' is already registered. To overwrite the existing configuration, re-run with --upgrade:

agents tool add local/run-migrations --config ./tools/run-migrations-v2.yaml --upgrade

agents tool remove

Purpose Remove a registered tool.

Arguments

<NAME>: Tool name to remove.
--yes: Skip confirmation prompt.

Examples

$ agents tool remove local/run-migrations Remove tool local/run-migrations? [y/N]: y ╭─ Tool Removed ────────────────────╮ │ Name: local/run-migrations │ │ Source: custom │ ╰───────────────────────────────────╯ ╭─ References ──────────────────────────────────────╮ │ Warning: This tool is referenced by: │ │ - Skill: local/devops-toolkit │ │ - Actor graph node: code_executor.run_db_migrate │ │ These references will break until resolved. │ ╰───────────────────────────────────────────────────╯

✓ OK Tool removed

agents tool list

Purpose List registered tools with optional filters.

Arguments

--namespace/-n NS: Filter by namespace.
--source SOURCE: Filter by tool source type (mcp, agent_skill, builtin, custom).
--format table|json: Output format.

Examples

$ agents tool list --namespace local --format table ╭─ Tools ──────────────────────────────────────────────────╮ │ Name Source Read-Only Writes │ │ ───────────────────────── ─────── ───────── ────── │ │ local/run-migrations custom — ✓ │ │ local/validate-api-compat custom — ✓ │ │ local/create-subplan custom — ✓ │ │ local/deploy-staging agent — ✓ │ ╰──────────────────────────────────────────────────────────╯ ╭─ Summary ────────╮ │ Total: 4 │ │ Read-Only: 0 │ │ Writes: 4 │ ╰──────────────────╯

✓ OK 4 tools listed

agents tool show

Purpose Show full details for a registered tool, including its schema, capability metadata, and where it is referenced.

Arguments

<NAME>: Tool name.
--format rich|json: Output format.

Examples

$ agents tool show local/run-migrations ╭─ Tool Details ──────────────────────────────╮ │ Name: local/run-migrations │ │ Description: Run database migrations │ │ Source: custom │ │ Config: ./tools/run-migrations.yaml │ │ Registered: 2026-02-09 10:15 │ ╰─────────────────────────────────────────────╯ ╭─ Input Schema ────────────────────────────────╮ │ direction: string (required) enum: [up, down] │ │ count: integer (default: 1) │ ╰───────────────────────────────────────────────╯ ╭─ Capability ──────────────────────╮ │ Read-Only: false │ │ Writes: true │ │ Write Scope: database:migrations │ │ Checkpointable: true │ │ Checkpoint Scope: transaction │ │ Side Effects: schema_mutation │ │ Idempotent: false │ ╰───────────────────────────────────╯ ╭─ Referenced By ───────────────────────╮ │ Skills: │ │ - local/devops-toolkit │ │ Actor Graph Nodes: │ │ - code_executor.run_db_migrate │ ╰───────────────────────────────────────╯

✓ OK Tool details loaded

agents resource type

Purpose Manage resource type definitions. Resource types are schema-level definitions that constrain categories of resources — they define what CLI arguments agents resource add <type> accepts, whether instances are physical or virtual, allowed parent/child types, auto-discovery behavior, sandbox strategy, and handler implementation. Built-in types (git-checkout, git, fs-mount, fs-directory, and their child types) are hardcoded. Custom types are defined in YAML configuration files and extend the system with new agents resource add subcommands.

agents resource type add

Purpose Register a new custom resource type from a YAML configuration file.

Arguments

<NAME>: Namespaced resource type name (e.g., local/svn, cleverthis/s3-bucket).
--config/-c FILE: Path to the resource type YAML configuration file.
--upgrade: If the type name already exists, overwrite it. Without this flag, adding a duplicate name fails with an error.

Examples

$ agents resource type add local/svn --config ./resource-types/svn.yaml ╭─ Resource Type ────────────────────╮ │ Name: local/svn │ │ Physical/Virtual: physical │ │ User Addable: yes │ │ Registered: 2026-02-09 10:15 │ ╰────────────────────────────────────╯ ╭─ CLI Arguments ────────────────────────╮ │ Argument Required Description │ │ ──────────── ──────── ───────────── │ │ --url yes Repository URL │ │ --checkout no Local checkout │ ╰────────────────────────────────────────╯ ╭─ Child Types ──────────────────────────╮ │ Auto-discover: svn-revision, svn-file │ │ Manual link: fs-mount │ ╰────────────────────────────────────────╯ ╭─ Sandbox ──────────────────────╮ │ Strategy: copy_on_write │ │ Handler: SVNHandler (custom) │ ╰────────────────────────────────╯

✓ OK Resource type registered ℹ New subcommand available: agents resource add local/svn

agents resource type remove

Purpose Remove a custom resource type. Built-in types cannot be removed. Fails if any registered resources use this type.

Arguments

<NAME>: Resource type name.
--yes: Skip confirmation prompt.

Examples

$ agents resource type remove local/svn Remove resource type local/svn? [y/N]: y ╭─ Resource Type Removed ───────╮ │ Name: local/svn │ │ Resources Using: 0 │ │ Subcommand Removed: yes │ ╰───────────────────────────────╯

✓ OK Resource type removed

agents resource type list

Purpose List all registered resource types (built-in and custom).

Arguments

--format table|json: Output format.

Examples

$ agents resource type list ╭─ Resource Types ───────── │ Name │ ───────────── │ git-checkout built-in physical yes │ git built-in physical yes │ │ git-remote built-in physical no │ git-branch built-in physical no │ git-tag built-in physical no │ git-commit built-in physical no │ git-tree built-in physical no │ git-tree-entry built-in physical no │ git-stash built-in physical no │ git-submodule built-in physical no │ fs-mount built-in physical yes │ fs-directory built-in physical yes │ │ fs-file built-in physical no │ fs-symlink built-in physical no │ fs-hardlink built-in physical no │ file built-in virtual no │ directory built-in virtual no │ symlink built-in virtual no │ commit built-in virtual no │ branch built-in virtual no │ tag built-in virtual no │ remote built-in virtual no │ submodule built-in virtual no │ tree built-in virtual no │ local/svn custom physical yes ╰─────────────── ─────────────────────────────────────────────────────────────────────────╮ Source Phys/Virt Addable Auto-children │ ────── ──────── ───────── ─────── ────────────────────────────────────── │ git, fs-directory │ git-remote, git-branch, git-tag, │ git-commit, git-stash, git-submodule │ (none) │ git-commit │ (none) │ git-tree │ git-tree-entry │ (none) │ (none) │ (none) │ fs-directory │ fs-file, fs-directory, │ fs-symlink, fs-hardlink │ (none) │ (none) │ (none) │ (none) │ (none) │ (none) │ (none) │ (none) │ (none) │ (none) │ (none) │ (none) │ svn-revision, svn-file │ ───────────────────────────────────────────────────────────────────────────────────╯ ╭─ Summary ─────────────────╮ │ Built-in: 24 │ │ Custom: 1 │ │ User Addable: 4 │ ╰───────────────────────────╯

✓ OK 25 resource types listed

agents resource type show

Purpose Show detailed information about a resource type, including its full schema.

Arguments

<NAME>: Resource type name.
--format rich|json: Output format.

Examples

$ agents resource type show git-checkout ╭─ Resource Type ──────────────────────────────────────────────────────╮ │ Name: git-checkout │ │ Source: built-in │ │ Description: A locally checked-out git repository with worktree │ │ Physical/Virtual: physical │ │ User Addable: yes │ ╰──────────────────────────────────────────────────────────────────────╯ ╭─ CLI Arguments (agents resource add git-checkout) ─────────────────╮ │ Argument Required Type Description │ │ ────────── ──────── ────── ────────────────────────────── │ │ --path yes path Local checkout directory │ │ --branch no string Default branch (default: main) │ ╰────────────────────────────────────────────────────────────────────╯ ╭─ Parent Types ───────────────╮ │ Allowed: (any, top-level OK) │ ╰──────────────────────────────╯ ╭─ Child Types ────────────────────────────────────────────────────╮ │ Type Auto Manual Link Description │ │ ───────────── ──── ─────────── ────────────────────────── │ │ git yes no Repo object DB and history │ │ fs-directory yes no Worktree root directory │ ╰──────────────────────────────────────────────────────────────────╯ ╭─ Sandbox ──────────────────────╮ │ Strategy: git_worktree │ │ Checkpointable: yes │ │ Handler: GitCheckoutHandler │ ╰────────────────────────────────╯

✓ OK Resource type details loaded

agents resource

Purpose Manage independently registered resources. Resources represent anything that can be read, written, or queried — git repositories, filesystems, databases, APIs, and more. Resources are registered independently of projects and linked to one or more projects via agents project link-resource. Resources form a directed acyclic graph (DAG) with parent/child relationships, and child resources are often auto-discovered when a parent resource is registered.

agents resource add

Purpose Register a new resource. The add command uses type-specific subcommands — each registered resource type (built-in or custom) provides its own subcommand with type-appropriate arguments.

Arguments

--description/-d TEXT: Optional resource description.
--upgrade: If the resource name already exists, overwrite it. Without this flag, adding a duplicate name fails with an error.
<TYPE>: Resource type name (e.g., git-checkout, git, fs-mount, fs-directory, local/svn). Determines type-specific flags.
<NAME>: Namespaced resource name (e.g., local/api-repo, cleverthis/staging-db).

Type-specific flags depend on the resource type. See agents resource type show <TYPE> for available arguments.

Examples

$ agents resource add git-checkout local/api-repo --path /home/user/projects/api-service --branch main ╭─ Resource ────────────────────────────╮ │ Name: local/api-repo │ │ Type: git-checkout │ │ Physical/Virtual: physical │ │ Path: /home/user/projects/api-service │ │ Branch: main │ │ Created: 2026-02-09 10:20 │ ╰───────────────────────────────────────╯ ╭─ Auto-discovered Children ───────────────────────────────────────╮ │ Name Type Status │ │ ─────────────────────────── ────────────── ───────────────── │ │ local/api-repo:repo git created │ │ local/api-repo:repo:origin git-remote created │ │ local/api-repo:repo:main git-branch created │ │ local/api-repo:repo:dev git-branch created │ │ local/api-repo:worktree fs-directory created │ │ + 47 git-commit resources │ │ + 312 git-tree-entry resources │ │ + 3 fs-directory + 28 fs-file │ ╰──────────────────────────────────────────────────────────────────╯ ╭─ Capabilities ─────────────────╮ │ Readable: yes │ │ Writable: yes │ │ Sandboxable: yes │ │ Checkpointable: yes │ │ Sandbox Strategy: git_worktree │ ╰────────────────────────────────╯

✓ OK Resource registered (395 child resources discovered)

$ agents resource add fs-mount local/docs --mount-path /docs/api-reference ╭─ Resource ──────────────────────────╮ │ Name: local/docs │ │ Type: fs-mount │ │ Physical/Virtual: physical │ │ Mount Path: /docs/api-reference │ │ Created: 2026-02-09 10:22 │ ╰─────────────────────────────────────╯ ╭─ Auto-discovered Children ────────────────────╮ │ + 1 fs-directory (root) │ │ + 3 fs-directory resources │ │ + 28 fs-file resources │ ╰───────────────────────────────────────────────╯ ╭─ Capabilities ──────────────────────╮ │ Readable: yes │ │ Writable: yes │ │ Sandboxable: yes │ │ Checkpointable: yes │ │ Sandbox Strategy: copy_on_write │ ╰─────────────────────────────────────╯

✓ OK Resource registered (31 child resources discovered)

Duplicate name error:

$ agents resource add git-checkout local/api-repo --path /repos/api-service

✗ Error: Resource local/api-repo already exists. Use --upgrade to overwrite: agents resource add --upgrade git-checkout local/api-repo --path /repos/api-service

agents resource remove

Purpose Remove a registered resource and all its auto-discovered child resources. Fails if the resource is linked to any project (unlink first).

Arguments

<NAME>: Resource name.
--yes: Skip confirmation prompt.

Examples

$ agents resource remove local/api-repo Remove resource local/api-repo and 362 child resources? [y/N]: y ╭─ Resource Removed ────────────────╮ │ Name: local/api-repo │ │ Type: git-checkout │ │ Children Removed: 395 │ │ Projects Unlinked: 0 │ ╰───────────────────────────────────╯

✓ OK Resource removed

agents resource list

Purpose List registered resources with optional filters.

Arguments

--namespace/-n NS: Filter by namespace.
--type/-t TYPE: Filter by resource type.
--format table|json: Output format.

Examples

$ agents resource list ╭─ Resources ──────────────────────────────────────────────────────────────────╮ │ Name Type Phys/Virt Children Projects │ │ ────────────────── ────────── ───────── ──────── ──────────────── │ │ local/api-repo git-checkout physical 395 local/api-service │ │ local/docs fs-mount physical 32 local/api-service │ │ local/staging-db database physical 12 local/api-service,│ │ local/staging │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Summary ───────────╮ │ Total: 3 │ │ Physical: 3 │ │ Virtual: 0 │ │ Total Children: 405 │ ╰─────────────────────╯

✓ OK 3 resources listed

agents resource show

Purpose Show detailed information about a registered resource including its type, capabilities, parent/child relationships, and linked projects.

Arguments

<NAME>: Resource name.
--format rich|json: Output format.

Examples

$ agents resource show local/api-repo ╭─ Resource ──────────────────────────────╮ │ Name: local/api-repo │ │ Type: git-checkout │ │ Physical/Virtual: physical │ │ Path: /home/user/projects/api-service │ │ Branch: main │ │ Created: 2026-02-09 10:20 │ ╰─────────────────────────────────────────╯ ╭─ Capabilities ──────────────────╮ │ Readable: yes │ │ Writable: yes │ │ Sandboxable: yes │ │ Checkpointable: yes │ │ Sandbox Strategy: git_worktree │ ╰─────────────────────────────────╯ ╭─ Parents ────╮ │ (top-level) │ ╰──────────────╯ ╭─ Direct Children ────────────────────────────────────────────╮ │ Name Type Auto Children │ │ ───────────────────────── ──────────── ──── ──────── │ │ local/api-repo:repo git yes 363 │ │ local/api-repo:worktree fs-directory yes 32 │ ╰──────────────────────────────────────────────────────────────╯ ╭─ Linked Projects ─────────────╮ │ - local/api-service (r/w) │ ╰───────────────────────────────╯ ╭─ Tool Bindings ────────────────────────────────╮ │ Tool Slot Access │ │ ──────────────────────── ───── ─────────── │ │ (builtin) git_status repo read_only │ │ (builtin) git_diff repo read_only │ │ (builtin) git_log repo read_only │ │ local/run-migrations db (not bound) │ ╰────────────────────────────────────────────────╯

✓ OK Resource details loaded

agents resource tree

Purpose Display the resource DAG as a tree starting from a given resource, showing parent/child relationships.

Arguments

<NAME>: Root resource name.
--depth/-d N: Maximum depth to display (default: 3).
--type/-t TYPE: Filter to only show children of a specific type.
--format tree|json: Output format.

Examples

$ agents resource tree local/api-repo --depth 2 ╭─ Resource Tree: local/api-repo ──────────────────────────────╮ │ │ │ local/api-repo (git-checkout, physical) │ │ ├── local/api-repo:repo (git, physical) │ │ │ ├── local/api-repo:repo:origin (git-remote) │ │ │ ├── local/api-repo:repo:main (git-branch) │ │ │ │ ├── ...repo:main:a1b2c3d (git-commit) │ │ │ │ └── ... 22 more git-commit resources │ │ │ └── local/api-repo:repo:dev (git-branch) │ │ │ └── ... 26 git-commit resources │ │ └── local/api-repo:worktree (fs-directory, physical) │ │ ├── ...worktree:src/ (fs-directory) │ │ ├── ...worktree:tests/ (fs-directory) │ │ └── ... 28 more fs-file resources │ │ │ ╰───────────────────────────────────────────────────────────────╯ ╭─ Summary ──────────────╮ │ Total shown: 14 │ │ Total in subtree: 395 │ │ Max depth: 2 │ ╰────────────────────────╯

✓ OK Resource tree displayed

agents resource link-child

Purpose Manually link one resource as a child of another. The child resource must already be registered. The resource types must be compatible (the parent type must allow the child type). A resource can have multiple parents.

Arguments

--parent/-p RESOURCE: Parent resource name.
--child/-c RESOURCE: Child resource name.

Examples

$ agents resource link-child --parent local/api-repo --child local/docs ╭─ Child Linked ────────────────────────╮ │ Parent: local/api-repo │ │ Child: local/docs │ │ Child Type: fs-mount │ │ Status: linked │ ╰───────────────────────────────────────╯

✓ OK Child resource linked

agents resource unlink-child

Purpose Remove a manual parent/child link between two resources. Auto-discovered links cannot be manually unlinked.

Arguments

--parent/-p RESOURCE: Parent resource name.
--child/-c RESOURCE: Child resource name.
--yes: Skip confirmation prompt.

Examples

$ agents resource unlink-child --parent local/api-repo --child local/docs Unlink local/docs from parent local/api-repo? [y/N]: y ╭─ Child Unlinked ──────────────────────╮ │ Parent: local/api-repo │ │ Child: local/docs │ │ Status: unlinked │ ╰───────────────────────────────────────╯

✓ OK Child resource unlinked

agents plan

Purpose Manage plans through the Action -> Strategize -> Execute -> Apply lifecycle.

agents plan list

Purpose List plans with optional filtering.

Arguments

--phase PHASE: Filter by phase.
--state STATE: Filter by processing state.
--project PROJECT: Filter by project.
--action ACTION: Filter by action name.
--format table|json: Output format.

Examples

$ agents plan list --phase execute --format table ╭─ Plans ──────────────────────────────────────────────────────────────────────────────╮ │ ID Phase State Action Project Elapsed │ │ ──────── ─────── ────────── ─────────────────── ───────────────── ───────── │ │ 01HXM7A9 execute processing local/code-coverage local/api-service 00:01:12 │ ╰──────────────────────────────────────────────────────────────────────────────────────╯ ╭─ Filters ──────╮ │ Phase: execute │ │ State: (any) │ │ Project: (any) │ │ Action: (any) │ ╰────────────────╯ ╭─ Summary ─────────╮ │ Total: 1 │ │ Processing: 1 │ │ Completed: 0 │ │ Errored: 0 │ ╰───────────────────╯

✓ OK 1 plan listed

agents plan use

Purpose Apply an action to one or more projects and start the Strategize phase.

Arguments

<ACTION_NAME>: Action name.
--project/-p PROJECT: Project name (repeatable).
--arg/-a name=value: Action argument (repeatable).
--automation-level manual|review|auto: Automation level.
--strategy-actor/-s ACTOR: Override the action's strategy actor for this plan.
--execution-actor/-e ACTOR: Override the action's execution actor for this plan.
--estimation-actor ACTOR: Override the action's estimation actor for this plan.
--invariant-actor ACTOR: Override the action's Invariant Reconciliation Actor for this plan.
--safety-profile NAME: Named safety profile.
--require-sandbox/--no-require-sandbox: Enforce sandboxing.
--require-checkpoints/--no-require-checkpoints: Enforce checkpoints.
--require-apply-approval/--no-require-apply-approval: Require human approval before apply.
--allow-skill-category NAME: Allow skill categories (repeatable).
--deny-skill-category NAME: Deny skill categories (repeatable).
--invariant TEXT: Invariant to attach to the created plan (repeatable). These are added as plan-level invariants in addition to any invariants inherited from the action, project, or global scope.

All actor arguments (--strategy-actor, --execution-actor, --estimation-actor, --invariant-actor) are optional overrides. When provided, they replace whatever was set when creating the action. When omitted, the action's configured actors are used.

Examples

$ agents plan use local/code-coverage --project local/api-service \ --arg target_coverage_percent=85 --automation-level review ╭─ Plan Created ──────────────────────╮ │ Plan ID: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Phase: strategize │ │ Action: local/code-coverage │ │ Project: local/api-service │ │ Automation: review │ │ Attempt: 1 │ ╰─────────────────────────────────────╯ ╭─ Inputs ─────────────────────╮ │ - target_coverage_percent=85 │ │ - safety_profile=default │ ╰──────────────────────────────╯ ╭─ Actors ────────────────────────╮ │ Strategy: local/strategist │ │ Execution: local/executor │ │ Estimation: (none) │ ╰─────────────────────────────────╯ ╭─ Safety ──────────────────╮ │ Sandbox: required │ │ Apply Approval: required │ │ Checkpoints: enabled │ │ Read-Only: no │ ╰───────────────────────────╯ ╭─ Context ───────────────────────╮ │ Resources: 2 (repo, db) │ │ Indexed Files: 347 │ │ View: strategize │ │ Hot Token Budget: 12,000 │ ╰─────────────────────────────────╯ ╭─ Next Steps ─────────────────────────────────────╮ │ - agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ - agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ - agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ ╰──────────────────────────────────────────────────╯

✓ OK Plan created

agents plan execute

Purpose Start or resume execution for a plan.

Arguments

[PLAN_ID]: Plan ID (optional if the most recent plan is unambiguous).

Examples

$ agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J ╭─ Execution ──────────────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Phase: execute │ │ Sandbox: git_worktree │ │ Worker: local/executor │ │ Started: 12:58:10 │ │ Attempt: 1 │ ╰──────────────────────────────────╯ ╭─ Sandbox ──────────────────────────────────╮ │ Strategy: git_worktree │ │ Path: /repos/api/.worktrees/plan-01HXM8 │ │ Branch: cleveragents/plan-01HXM8C2 │ │ Status: active │ ╰────────────────────────────────────────────╯ ╭─ Strategy Summary ─────────────────────╮ │ Decisions: 8 │ │ Invariants: 2 │ │ Planned Child Plans: 2+ │ │ Estimated Files: ~12 │ │ Risk: low │ ╰────────────────────────────────────────╯ ╭─ Progress ────────╮ │ ⏳ Collect context │ │ • Run tools │ │ • Build changeset │ │ • Validate │ ╰───────────────────╯

✓ OK Execution started

agents plan apply

Purpose Apply sandboxed changes to real resources.

Arguments

<PLAN_ID>: Plan ID.
--yes: Skip confirmation.

Examples

$ agents plan apply 01HXM8C2ZK4Q7C2B3F2R4VYV6J Apply changes for plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J? [y/N]: y ╭─ Apply Summary ─────────────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Artifacts: 6 files updated │ │ Changes: 42 insertions, 9 deletions │ │ Project: local/api-service │ │ Applied At: 2026-02-08 13:04 │ ╰─────────────────────────────────────╯ ╭─ Validation ───────────────────╮ │ Tests: passed (24/24) │ │ Lint: passed (0 warnings) │ │ Type Check: passed (0 errors) │ │ Duration: 12.4s │ ╰────────────────────────────────╯ ╭─ Sandbox Cleanup ─────────╮ │ Worktree: removed │ │ Branch: merged to main │ │ Checkpoint: archived │ ╰───────────────────────────╯ ╭─ Plan Lifecycle ────────────────────────╮ │ Phase: applied │ │ State: complete │ │ Total Duration: 00:06:14 │ │ Total Cost: $0.0847 │ │ Decisions Made: 8 │ │ Child Plans: 2 (completed) │ ╰─────────────────────────────────────────╯ ╭─ Next Steps ──────╮ │ - Review git diff │ │ - Commit changes │ ╰───────────────────╯

✓ OK Changes applied

agents plan status

Purpose Show detailed status for a plan.

Arguments

[PLAN_ID]: Plan ID (optional if the most recent plan is unambiguous).

Examples

$ agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J ╭─ Plan Status ────────────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Phase: execute │ │ State: processing │ │ Action: local/code-coverage │ │ Project: local/api-service │ │ Automation: review │ │ Attempt: 1 │ ╰──────────────────────────────────╯ ╭─ Progress ───────╮ │ ✓ Strategize │ │ ⏳ Execute │ │ • Apply (queued) │ ╰──────────────────╯ ╭─ Timing ──────────╮ │ Started: 12:57:01 │ │ Elapsed: 00:01:12 │ │ ETA: 00:03:45 │ ╰───────────────────╯ ╭─ Execution Detail ──────────╮ │ Sandbox: git_worktree │ │ Tool Calls: 8 │ │ Files Modified: 3 │ │ Child Plans: 1/2 complete │ │ Checkpoints: 2 created │ ╰─────────────────────────────╯ ╭─ Cost ───────────────╮ │ Tokens Used: 12,420 │ │ Cost So Far: $0.041 │ │ Estimated: $0.085 │ ╰──────────────────────╯

✓ OK Status refreshed

agents plan cancel

Purpose Cancel a plan that is not terminal.

Arguments

<PLAN_ID>: Plan ID.
--reason/-r TEXT: Optional reason.

Examples

$ agents plan cancel 01HXM8C2ZK4Q7C2B3F2R4VYV6J --reason "blocked on credentials" ╭─ Plan Cancelled ─────────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Phase: execute │ │ Reason: blocked on credentials │ │ State: cancelled │ │ Cancelled At: 13:02:15 │ ╰──────────────────────────────────╯ ╭─ Sandbox ────────────────╮ │ Status: preserved │ │ Files Modified: 3 │ │ Checkpoints: 2 │ ╰──────────────────────────╯ ╭─ Child Plans ─────────────╮ │ Completed: 1 │ │ Cancelled: 1 │ │ Artifacts Preserved: yes │ ╰───────────────────────────╯ ╭─ Recovery ────────────────────────────────────────╮ │ - Resolve credentials │ │ - Run agents plan resume 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ ╰───────────────────────────────────────────────────╯

✓ OK Plan cancelled

agents plan tree

Purpose Render the decision tree for a plan.

Arguments

[PLAN_ID]: Plan ID (optional if a current plan exists).
--format tree|json|flat: Output format.
--show-superseded: Include superseded decisions.

Examples

$ agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J ╭─ Decision Tree ──────────────────────────────────────────────────────────────────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ ├─ [prompt_definition] "Increase test coverage to 85%" │ │ ├─ [invariant_enforced] "Prioritize financial transaction and user mgmt code" │ │ ├─ [invariant_enforced] "All API calls over TCP must be mocked" │ │ ├─ [strategy_choice] "Prioritize auth and payments" (confidence: 0.82) │ │ ├─ [subplan_parallel_spawn] "Implement auth and payment modules, in parallel" │ │ │ ├─ [subplan_spawn] "Write auth tests" → Plan: 01HXM9F1A │ │ │ └─ [subplan_spawn] "Write payment tests" → Plan: 01HXM9F2B │ │ └─ [subplan_parallel_spawn] "Write tests for remaining modules" │ │ └─ ... │ ╰──────────────────────────────────────────────────────────────────────────────────────────╯ ╭─ Tree Summary ─────────────╮ │ Nodes: 9 │ │ Depth: 3 │ │ Child Plans: 2+ │ │ Invariants: 2 │ │ Superseded: 0 (hidden) │ ╰────────────────────────────╯ ╭─ Child Plans ──────────────────────────────────────╮ │ ID Name Phase State │ │ ────────── ───────────── ─────── ───────── │ │ 01HXM9F1A auth-tests execute processing │ │ 01HXM9F2B payment-tests execute queued │ ╰────────────────────────────────────────────────────╯ ╭─ Decision IDs (for correction) ──────────────────╮ │ Root: 01HXM9A0B1Q2W3R5G8Z0P4Q1X8 │ │ Invariant 1: 01HXM9A0C1R3X4S6G9Z1P5Q2Y9 │ │ Invariant 2: 01HXM9A0D2S4Y5T7H0Z2P6Q3Z0 │ │ Strategy: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 │ │ Parallel 1: 01HXM9A1D3R8X5S7H1Z2P5Q2Y0 │ │ Spawn Auth: 01HXM9A2D3Q8W4R6H9Z1P5Q2X0 │ │ Spawn Payment: 01HXM9A3E4Q9W5R7I0Z2P6Q3X1 │ │ Parallel 2: 01HXM9A4F5Q0W6R8J1Z3P7Q4X2 │ ╰──────────────────────────────────────────────────╯

✓ OK Decision tree rendered

agents plan explain

Purpose Show a detailed explanation for a decision.

Arguments

<DECISION_ID>: Decision ID.
--show-context: Include the context snapshot.
--show-reasoning: Include raw model reasoning if available.

Examples

$ agents plan explain 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 ╭─ Decision ─────────────────────────────────────╮ │ ID: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 │ │ Type: strategy_choice │ │ Question: Which modules should be prioritized? │ │ Chosen: Auth and payments │ │ Confidence: 0.82 │ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Sequence: 2 of 5 │ │ Created: 2026-02-08 12:58 │ ╰────────────────────────────────────────────────╯ ╭─ Alternatives Considered ──────────────────────╮ │ 1. Auth and payments (chosen) │ │ 2. User module first (coverage 71%, med risk) │ │ 3. All modules equally (spread thin) │ ╰────────────────────────────────────────────────╯ ╭─ Impact ──────────────────────╮ │ Downstream Decisions: 3 │ │ Downstream Child Plans: 2 │ │ Artifacts Produced: 5 │ │ Correction Impact: medium │ ╰───────────────────────────────╯ ╭─ Context Snapshot ───────────────╮ │ - Coverage < 70% in auth │ │ - Payments failures last release │ │ - Auth: 12 files, 45% coverage │ │ - Payments: 8 files, 52% cover. │ │ Hot Context Hash: sha256:4b2e... │ ╰──────────────────────────────────╯ ╭─ Rationale ───────────────────────────────────────╮ │ Auth and payment modules have the lowest coverage │ │ and highest business risk. Auth handles security │ │ tokens, payments handles money. Both had bugs in │ │ the last release traceable to missing tests. │ ╰───────────────────────────────────────────────────╯ ╭─ Correction ──────────────────────────────────────────────╮ │ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 │ │ --mode revert --guidance "Prioritize payments first..." │ ╰───────────────────────────────────────────────────────────╯

✓ OK Decision explained

agents plan correct

Purpose Correct a decision either by reverting and re-executing or by appending a fix.

Arguments

<DECISION_ID>: Decision ID.
--mode revert|append: Correction mode.
--guidance/-g TEXT: Guidance text.
--dry-run: Show impact without executing.
--yes: Skip confirmation for revert mode.

Examples

$ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert \ --guidance "Prioritize payments first" --yes ╭─ Correction ─────────────────────────────────────╮ │ Mode: revert │ │ Impact: 3 decisions, 2 child plans, 5 artifacts │ │ New Decision: 01HXM9B7Z3Q1Q8K2E9H7K3W2M8 │ │ Corrects: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 │ │ Attempt: 2 │ ╰──────────────────────────────────────────────────╯ ╭─ Affected Subtree ──────────────╮ │ Decisions Invalidated: 3 │ │ Child Plans Rolled Back: 2 │ │ Artifacts Archived: 5 │ │ Unaffected Decisions: 2 │ ╰─────────────────────────────────╯ ╭─ Sandbox Rollback ─────────────╮ │ Checkpoint: cp_01HXM8C2 │ │ Files Reverted: 5 │ │ Status: restored │ ╰────────────────────────────────╯ ╭─ Recompute ──────────────╮ │ Queued: 2 child plans │ │ ETA: 4m │ ╰──────────────────────────╯ ╭─ History ──────────────────────────────────────────╮ │ - Original decision superseded │ │ - Prior artifacts archived for comparison │ │ - agents plan diff --correction 01HXM9B7Z3Q1Q8K2.. │ ╰─────────────────────────────────────────────────────╯

✓ OK Correction applied

agents plan diff

Purpose Show diffs for a plan or a correction attempt.

Arguments

--plan <PLAN_ID>: Show diff for a plan.
--correction <CORRECTION_ATTEMPT_ID>: Compare correction outputs.

Examples


$ agents plan diff --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J
╭─ Diff Summary ─────────────────────────────────╮
│ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J            │
│ Project: local/api-service                  │
│ Files Changed: 2                             │
│ Insertions: 12                               │
│ Deletions: 4                                 │
│ Net Change: +8 lines                         │
╰────────────────────────────────────────────────╯
╭─ Files ───────────────────────────────╮
│ Path                 Change  Status   │
│ ───────────────────  ──────  ──────── │
│ src/auth/session.py  +8 -2   modified │
│ src/auth/tokens.py   +4 -2   modified │
╰───────────────────────────────────────╯
╭─ Patch Preview ─────────────────────────╮
│ --- a/src/auth/session.py              │
│ +++ b/src/auth/session.py              │
│ @@ -12,4 +12,10 @@                      │
│ - import jwt                            │
│ + import sessionlib                     │
│ - def validate_token(...)               │
│ + def validate_session(...)             │
│ --- a/src/auth/tokens.py               │
│ +++ b/src/auth/tokens.py               │
│ @@ -5,3 +5,7 @@                         │
│ - TOKEN_EXPIRY = 3600                    │
│ + TOKEN_EXPIRY = 7200                    │
╰─────────────────────────────────────────╯
╭─ Risk Assessment ────────────────╮
│ API Compatibility: preserved    │
│ Test Coverage: maintained       │
│ Breaking Changes: none detected │
╰──────────────────────────────────╯
✓ OK Diff generated

agents plan artifacts

Purpose List artifacts produced by a plan.

Arguments

<PLAN_ID>: Plan ID.

Examples

$ agents plan artifacts 01HXM8C2ZK4Q7C2B3F2R4VYV6J ╭─ Artifacts ──────────────────────────────────────────────╮ │ Path Type Size Change Child Plan │ │ ───────────────────── ───── ────── ───────── ─────── │ │ src/auth/session.py write 2.1 KB +8 -2 root │ │ tests/test_session.py write 4.7 KB +47 -0 root │ │ src/auth/tokens.py edit 1.8 KB +4 -2 root │ │ tests/test_tokens.py write 3.2 KB +32 -0 auth │ ╰──────────────────────────────────────────────────────────╯ ╭─ Summary ──────────╮ │ Total: 4 │ │ Writes: 2 (new) │ │ Edits: 2 (modified) │ │ Deletes: 0 │ │ Total Size: 11.8 KB │ ╰────────────────────╯ ╭─ By Plan ─────────────────╮ │ Root Plan: 3 artifacts │ │ auth-tests: 1 artifact │ │ payment-tests: (pending) │ ╰───────────────────────────╯

✓ OK 4 artifacts listed

agents plan prompt

Purpose Provide additional guidance to a plan, typically when it is errored or awaiting input.

Arguments

<PLAN_ID>: Plan ID.
"<GUIDANCE>": Guidance text.

Examples

$ agents plan prompt 01HXM8C2ZK4Q7C2B3F2R4VYV6J "Use mocks for database tests" ╭─ Guidance Added ───────────────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Guidance: Use mocks for database tests │ │ Scope: next execution step │ │ Phase: execute │ │ State: errored → processing │ ╰────────────────────────────────────────╯ ╭─ Decision Created ────────────────────────╮ │ Type: user_intervention │ │ ID: 01HXM9C5G7R2X8S3K4Z5Q8R6Y3 │ │ Parent: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 │ ╰───────────────────────────────────────────╯ ╭─ Queue ────╮ │ Pending: 1 │ │ Applied: 0 │ ╰────────────╯

✓ OK Guidance queued

agents plan resume

Purpose Resume an interrupted plan from its last checkpoint.

Arguments

<PLAN_ID>: Plan ID.

Examples

$ agents plan resume 01HXM8C2ZK4Q7C2B3F2R4VYV6J ╭─ Plan Resumed ───────────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Checkpoint: cp_01HXM8C2 │ │ Phase: execute │ │ State: processing │ │ Attempt: 2 │ ╰──────────────────────────────────╯ ╭─ Checkpoint Details ──────────────╮ │ Label: before auth refactor │ │ Created: 2026-02-08 13:04 │ │ Files at Checkpoint: 3 │ │ Decisions at Checkpoint: 2 │ ╰───────────────────────────────────╯ ╭─ Pending Guidance ─────────────────╮ │ 1. Use mocks for database tests │ ╰────────────────────────────────────╯

✓ OK Plan resumed

agents plan rollback

Purpose Rollback a plan sandbox to a checkpoint.

Arguments

<PLAN_ID>: Plan ID.
<CHECKPOINT_ID>: Checkpoint ID.
--yes: Skip confirmation.

Examples

$ agents plan rollback 01HXM8C2ZK4Q7C2B3F2R4VYV6J cp_01HXM8C2 Rollback plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J to cp_01HXM8C2? [y/N]: y ╭─ Rollback Summary ───────────────╮ │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │ │ Checkpoint: cp_01HXM8C2 │ │ Label: before auth refactor │ │ Files: 6 reverted │ ╰──────────────────────────────────╯ ╭─ Changes Reverted ──────────────────╮ │ File Action │ │ ────────────────────── ────────── │ │ src/auth/session.py restored │ │ src/auth/tokens.py restored │ │ tests/test_session.py removed │ │ tests/test_tokens.py removed │ │ src/auth/fixtures.py restored │ │ src/auth/__init__.py restored │ ╰─────────────────────────────────────╯ ╭─ Impact ──────────────────────────────╮ │ Child Plans Invalidated: 2 │ │ Sandbox: restored to cp_01HXM8C2 │ │ Decisions After CP: 2 discarded │ │ Tool Calls After CP: 5 undone │ ╰───────────────────────────────────────╯ ╭─ Post-Rollback State ─────────╮ │ Phase: execute │ │ State: queued (awaiting input) │ │ Checkpoints Remaining: 2 │ ╰───────────────────────────────╯

✓ OK Rollback complete

agents action

Purpose Manage reusable actions.

agents action create

Purpose Create a new action template.

Arguments

<NAME>: Namespaced action name.
--strategy-actor/-s ACTOR: Strategize actor.
--execution-actor/-e ACTOR: Execution actor.
--definition-of-done/-d TEXT: Completion criteria.
--description TEXT: Short description.
--long-description TEXT: Long description.
--arg/-a spec: Argument definition (repeatable).
--reusable/--no-reusable: Keep action after use.
--read-only: Read-only action.
--available: Make action available immediately.
--estimation-actor ACTOR: Optional estimation actor.
--invariant-actor ACTOR: Invariant Reconciliation Actor for this action. Carried forward to plans created from this action (can be overridden via agents plan use --invariant-actor).
--safety-profile NAME: Named safety profile.
--require-sandbox/--no-require-sandbox: Enforce sandboxing.
--require-checkpoints/--no-require-checkpoints: Enforce checkpoints.
--require-apply-approval/--no-require-apply-approval: Require approval before apply.
--allow-skill-category NAME: Allow skill categories.
--deny-skill-category NAME: Deny skill categories.
--invariant TEXT: Invariant to attach to this action (repeatable). These invariants are carried forward as plan-level invariants when the action is used.

Examples

$ agents action create local/code-coverage \ --strategy-actor local/strategist \ --execution-actor local/executor \ --definition-of-done "Coverage reaches 85%" \ --arg "target_coverage_percent:int:required:Target coverage percentage" \ --available ╭─ Action Created ──────────────────────╮ │ Name: local/code-coverage │ │ ID: 01HXMAY3D1JQ0C3G1H0Q7B2W7M │ │ State: available │ │ Strategy Actor: local/strategist │ │ Execution Actor: local/executor │ │ Reusable: yes │ │ Read Only: no │ │ Created: 2026-02-08 12:20 │ ╰───────────────────────────────────────╯ ╭─ Definition of Done ─╮ │ Coverage reaches 85% │ ╰──────────────────────╯ ╭─ Arguments ──────────────────────────────────────────────────────╮ │ Name Type Required Description │ │ ─────────────────────── ────── ──────── ───────────────────── │ │ target_coverage_percent int yes Target coverage % │ │ test_command string no Test framework to use │ ╰──────────────────────────────────────────────────────────────────╯ ╭─ Safety ──────────────────╮ │ Sandbox: required │ │ Apply Approval: required │ │ Checkpoints: enabled │ │ Skill Allow: (all) │ │ Skill Deny: (none) │ ╰───────────────────────────╯ ╭─ Usage ─────────────────────────────────────────────────────────────────╮ │ agents plan use local/code-coverage --project local/api-service │ │ --arg target_coverage_percent=85 │ ╰─────────────────────────────────────────────────────────────────────────╯

✓ OK Action created

agents action list

Purpose List actions with optional filters.

Arguments

--namespace/-n NS: Filter by namespace.
--state/-s STATE: Filter by state.
--available: Show only available actions.

Examples

$ agents action list --available ╭─ Actions ──────────────────────────────────────────────────────────────────────────────────╮ │ Name State Strategy Actor Execution Actor Reusable Plans │ │ ─────────────────── ───────── ──────────────── ─────────────── ──────── ───── │ │ local/code-coverage available local/strategist local/executor ✓ 3 │ ╰──────────────────────────────────────────────────────────────────────────────────────────╯ ╭─ Filters ────────╮ │ State: available │ │ Namespace: (any) │ ╰──────────────────╯ ╭─ Summary ────────────╮ │ Total: 1 │ │ Available: 1 │ │ Draft: 0 │ │ Archived: 0 │ │ Total Plans Created: 3 │ ╰──────────────────────╯

✓ OK 1 action listed

agents action show

Purpose Show details for an action.

Arguments

<ACTION_ID|NAME>: Action ID or name.

Examples

$ agents action show local/code-coverage ╭─ Action Details ──────────────────────╮ │ Name: local/code-coverage │ │ ID: 01HXMAY3D1JQ0C3G1H0Q7B2W7M │ │ State: available │ │ Strategy Actor: local/strategist │ │ Execution Actor: local/executor │ │ Reusable: yes │ │ Read Only: no │ │ Created: 2026-02-08 12:20 │ ╰───────────────────────────────────────╯ ╭─ Definition of Done ─╮ │ Coverage reaches 85% │ ╰──────────────────────╯ ╭─ Arguments ──────────────────────────────────────────────────────╮ │ Name Type Required Description │ │ ─────────────────────── ────── ──────── ───────────────────── │ │ target_coverage_percent int yes Target coverage % │ │ test_command string no Test framework to use │ ╰──────────────────────────────────────────────────────────────────╯ ╭─ Safety ──────────────────╮ │ Sandbox: required │ │ Apply Approval: required │ │ Checkpoints: enabled │ ╰───────────────────────────╯ ╭─ History ────────────────────╮ │ Plans Created: 3 │ │ Plans Completed: 2 │ │ Plans Failed: 0 │ │ Avg Duration: 00:04:30 │ │ Avg Cost: $0.072 │ ╰──────────────────────────────╯ ╭─ Usage ───────────────────────────────────────────────────────────╮ │ - agents plan use local/code-coverage --project local/api-service │ │ --arg target_coverage_percent=85 │ ╰───────────────────────────────────────────────────────────────────╯

✓ OK Action loaded

agents action available

Purpose Mark a draft action as available.

Arguments

<ACTION_ID|NAME>: Action ID or name.

Examples

$ agents action available 01HXMAY3D1JQ0C3G1H0Q7B2W7M ╭─ Action Available ─────────────╮ │ ID: 01HXMAY3D1JQ0C3G1H0Q7B2W7M │ │ State: draft → available │ │ Name: local/code-coverage │ ╰────────────────────────────────╯ ╭─ Visibility ─────╮ │ Namespace: local │ │ Listed: yes │ │ Usable: yes │ ╰──────────────────╯ ╭─ Validation ────────────────────────╮ │ Strategy Actor: resolved │ │ Execution Actor: resolved │ │ Definition of Done: present │ │ Arguments: valid schema │ ╰─────────────────────────────────────╯

✓ OK Action marked available

agents action archive

Purpose Archive an action.

Arguments

<ACTION_ID|NAME>: Action ID or name.

Examples

$ agents action archive local/old-action ╭─ Action Archived ──────────╮ │ Name: local/old-action │ │ State: available → archived │ │ Archived: 2026-02-08 12:22 │ ╰────────────────────────────╯ ╭─ Impact ───────────────────────╮ │ Availability: hidden from list │ │ Existing Plans: unchanged │ │ Active Plans: 0 affected │ ╰────────────────────────────────╯ ╭─ History ─────────────────╮ │ Total Plans: 5 │ │ Completed: 4 │ │ Failed: 1 │ │ Last Used: 2026-02-06 │ ╰───────────────────────────╯

✓ OK Action archived

agents config

Purpose Manage global configuration values.

agents config set

Purpose Set a configuration key.

Arguments

<key>: automation-level, default-actor, log-level, invariant-actor.
<value>: Value to set.

The invariant-actor key sets the default Invariant Reconciliation Actor used globally. This actor is used to reconcile invariant conflicts when neither the plan nor the project specifies one.

Examples

$ agents config set automation-level review ╭─ Config Updated ──────────────╮ │ Key: automation-level │ │ Value: review │ │ Previous: manual │ │ Source: config │ │ Scope: global │ ╰──────────────────────────────╯ ╭─ Effective ────────────────────────╮ │ Sessions: new sessions │ │ Plans: future plans (unless set) │ │ Existing: unchanged │ ╰────────────────────────────────────╯ ╭─ Saved To ──────────────────────────╮ │ File: ~/.cleveragents/config.toml │ │ Line: 8 │ ╰─────────────────────────────────────╯

✓ OK Config updated

agents config get

Purpose Get a configuration value.

Arguments

<key>: Key to read.

Examples

$ agents config get default-actor ╭─ Config ──────────────────╮ │ Key: default-actor │ │ Value: local/orchestrator │ │ Source: config │ │ Overridden: no │ │ Type: string │ ╰───────────────────────────╯ ╭─ Origin ──────────────────────────╮ │ File: ~/.cleveragents/config.toml │ │ Line: 12 │ │ Default: local/orchestrator │ ╰───────────────────────────────────╯ ╭─ Resolution Chain ──────────────╮ │ 1. CLI flag: (not set) │ │ 2. Env var: (not set) │ │ 3. Config file: local/orchestra │ │ 4. Default: local/orchestrator │ │ Winner: config file (level 3) │ ╰─────────────────────────────────╯

✓ OK Config read

agents config list

Purpose List all configuration values.

Arguments

None.

Examples

$ agents config list ╭─ Config ───────────────────────────────────────────────╮ │ Key Value Source Modified │ │ ──────────────── ────────────────── ─────── ──────── │ │ automation-level review config yes │ │ default-actor local/orchestrator config yes │ │ invariant-actor local/reconciler config yes │ │ log-level INFO default no │ │ sandbox-required true default no │ │ apply-approval true default no │ ╰────────────────────────────────────────────────────────╯ ╭─ Overrides ─────╮ │ Env: none │ │ CLI Flags: none │ ╰─────────────────╯ ╭─ Config File ───────────────────────╮ │ Path: ~/.cleveragents/config.toml │ │ Size: 284 bytes │ │ Valid: yes │ ╰─────────────────────────────────────╯

✓ OK 6 settings listed

agents providers

Purpose Inspect provider availability.

agents providers list

Purpose List available providers and whether credentials are configured.

Arguments

None.

Examples

$ agents providers list ╭─ Providers ───────────────────────────────────────────────────────╮ │ Provider Status Default Model Models Available │ │ ────────── ─────────── ───────────── ──────────────── │ │ openai missing key gpt-4 4 │ │ anthropic configured claude-3.5 3 │ │ openrouter configured gpt-4o 12 │ │ google missing key gemini-2.0 2 │ ╰──────────────────────────────────────────────────────────────────╯ ╭─ Credentials ─╮ │ Configured: 2 │ │ Missing: 2 │ ╰───────────────╯ ╭─ Routing ──────────────────────╮ │ Default: anthropic/claude-3.5 │ │ Fallback: openrouter/gpt-4o │ ╰────────────────────────────────╯ ╭─ Key Sources ─────────────────────╮ │ anthropic: ANTHROPIC_API_KEY │ │ openrouter: OPENROUTER_API_KEY │ │ openai: OPENAI_API_KEY (missing) │ │ google: GOOGLE_API_KEY (missing) │ ╰───────────────────────────────────╯ ╭─ Rate Limits ───────────────╮ │ anthropic: 1M tokens/min │ │ openrouter: 500K tok/min │ ╰─────────────────────────────╯

✓ OK Providers listed

agents invariant

Purpose Manage invariants — named constraints that guide and constrain plan execution. Invariants can be attached to any scope: global (all plans), project (all plans targeting that project), plan (a specific plan and its child plans), or action (carried forward when the action is used). Exactly one scope flag is required for add and list.

agents invariant add

Purpose Add an invariant at the specified scope.

Arguments

"<TEXT>": The invariant text.
--global: Attach as a global invariant (applies to all plans).
--project/-p PROJECT: Attach to a project (applies to all plans targeting this project).
--plan PLAN_ID: Attach to a plan (applies to this plan and its child plans).
--action ACTION: Attach to an action (carried forward when the action is used via agents plan use).

Exactly one of --global, --project, --plan, or --action must be provided.

Examples


$ agents invariant add --global "All public APIs must maintain backward compatibility"
╭─ Invariant Added ──────────────────────────────────────────────────────╮
│ Invariant: All public APIs must maintain backward compatibility      │
│ Scope: global                                                       │
│ ID: inv_01HXM9A1B                                                  │
╰────────────────────────────────────────────────────────────────────────╯
✓ OK Invariant added
$ agents invariant add --project local/api-service "All endpoints must validate auth tokens"
╭─ Invariant Added ──────────────────────────────────────────────╮
│ Project: local/api-service                                   │
│ Invariant: All endpoints must validate auth tokens           │
│ Scope: project                                              │
│ ID: inv_01HXM9A2C                                           │
╰────────────────────────────────────────────────────────────────╯
✓ OK Invariant added
$ agents invariant add --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J "All database queries must use parameterized statements"
╭─ Invariant Added ─────────────────────────────────────────────────────╮
│ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J                                    │
│ Invariant: All database queries must use parameterized statements    │
│ Scope: plan                                                        │
│ ID: inv_01HXM9G3A                                                  │
╰───────────────────────────────────────────────────────────────────────╯
✓ OK Invariant added
$ agents invariant add --action local/code-coverage "Test files must not import production secrets"
╭─ Invariant Added ──────────────────────────────────────────────────────╮
│ Action: local/code-coverage                                        │
│ Invariant: Test files must not import production secrets             │
│ Scope: action                                                      │
│ ID: inv_01HXM9H4B                                                  │
╰────────────────────────────────────────────────────────────────────────╯
✓ OK Invariant added

agents invariant list

Purpose List invariants at a given scope. Use --effective with --plan to show the final reconciled view of invariants (after precedence resolution) rather than just the invariants directly attached at that scope.

Arguments

--global: List global invariants.
--project/-p PROJECT: List invariants attached to a project.
--plan PLAN_ID: List invariants attached to a plan.
--action ACTION: List invariants attached to an action.
--effective: (Only with --plan) Show the reconciled invariant view after precedence resolution across all scopes.
--format table|json: Output format (default: table).

Examples

$ agents invariant list --global ╭─ Global Invariants ──────────────────────────────────────────────────────╮ │ ID Text │ │ ────────────── ──────────────────────────────────────────────────── │ │ inv_01HXM9A1B All public APIs must maintain backward compatibility │ │ inv_01HXM9A1C Payment processing must be idempotent │ ╰──────────────────────────────────────────────────────────────────────────╯ ✓ OK 2 invariants $ agents invariant list --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J --effective ╭─ Effective Invariants (Plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J) ─────────────────────────────────╮ │ ID Source Text │ │ ────────────── ─────── ────────────────────────────────────────────────────── │ │ inv_01HXM9A1B global All public APIs must maintain backward compatibility │ │ inv_01HXM9A2C project All endpoints must validate auth tokens │ │ inv_01HXM9G3A plan All database queries must use parameterized statements │ ╰───────────────────────────────────────────────────────────────────────────────────────────╯ │ Conflicts Resolved: 1 │ │ Global "Use shared DB pool" overridden by plan "All database queries must use │ │ parameterized statements" │

✓ OK 3 effective invariants (1 global, 1 project, 1 plan; 1 conflict resolved)

agents invariant remove

Purpose Remove an invariant by ID. The invariant is removed from whichever scope it was originally attached to.

Arguments

<INVARIANT_ID>: Invariant ID to remove.
--yes: Skip confirmation.

Examples

$ agents invariant remove inv_01HXM9A1C Remove invariant inv_01HXM9A1C ("Payment processing must be idempotent", scope: global)? [y/N]: y ╭─ Invariant Removed ──────────────────────────────────────────────╮ │ Removed: Payment processing must be idempotent │ │ Scope: global │ │ ID: inv_01HXM9A1C │ ╰──────────────────────────────────────────────────────────────────╯

✓ OK Invariant removed

Core Concepts

Plan

A plan is the fundamental unit of orchestration and traceability.

Plan Lifecycle Phases

A plan always moves through the following phases, in order:

Action → Strategize → Execute → Apply → Applied (terminal)

In this spec:

Strategize is the phase name (the output is a strategy).
Execute is the phase name (the output is a changeset).
Apply is the phase name (the output is an applied change).
Applied is the resulting terminal state after Apply succeeds.

This four-stage model is explicitly called out as the new architecture replacing a prior linear pipeline.

Phase Transition Verbs (CLI / UX Contract)

Verbs that trigger phase transitions. CleverAgents should standardize these verbs as the public API (CLI, TUI, web):

Current Phase	Command Verb	Next Phase
(none)	`create`	Action
Action	`use`	Strategize
Strategize	`execute`	Execute
Execute	`apply`	Applied

Important behavioral rule: CleverAgents must support multiple "automation levels" that can automatically progress through these verbs without the user explicitly issuing them, but the verbs remain the conceptual contract.

Plan States (Per Phase)

A plan's phase indicates "what step of the lifecycle it is in." Separately, the plan has a processing state indicating "what is happening right now."

Recommended state model:

Action phase states
- available (action exists and can be used)
- draft (action is being authored/edited)
- archived (soft-deleted or hidden, optional)
Strategize / Execute / Apply phase states
- queued (waiting for compute/worker)
- processing (currently running)
- errored (failed; includes error metadata)
- complete (finished successfully)
- cancelled (user/system cancelled; safe terminal for that phase)

Plan Identity and Traceability

Every plan should have:

plan_id: Unique, immutable ID (UUID or ULID).
parent_plan_id: Nullable; present for child plans.
root_plan_id: The top-most plan in the tree.
attempt: An integer attempt counter that increments when re-running a phase (e.g., re-executing after a fix).
created_at / updated_at / completed_at timestamps.
created_by (user identity / session identity).

Plan Hierarchy and Parallelism

A single plan should usually represent the smallest "complete" unit of work (similar to what would fit in one git commit). However:

Plans are hierarchical. A child plan is simply a Plan with a parent — it follows the same lifecycle, has the same data model, and is functionally identical to a root plan except that it has a parent_plan_id.
Decisions about child plans are made during Strategize (as subplan_spawn decision types). Multiple child plans that should execute concurrently are grouped under a subplan_parallel_spawn decision.
Child plans are actually spawned during Execute (based on those decisions).
Child plans can run in parallel (via subplan_parallel_spawn) or sequentially (via individual subplan_spawn decisions). Without a subplan_parallel_spawn wrapper, each subplan_spawn decision results in sequential execution.
Applicable invariants are enforced during Strategize by adding invariant_enforced decisions to the tree, which constrain downstream decisions and child plans.
The parent plan is responsible for merging results.

This is core to the long-term objective: tackling large tasks while only recomputing parts of the decision tree when corrected.

Hierarchical Decomposition for Scale

When handling massive tasks (e.g., converting Firefox to Rust), the system uses hierarchical decomposition. Each level spawns child plans (which are themselves full Plans with their own decision trees):

Root Plan: High-level architectural decisions and invariants
- "Convert Firefox Renderer to Rust"
- Invariant: "Maintain API compatibility with existing C++ callers"
- Decision: "Start with leaf modules, work inward"
- Context: Module dependency graph (2,847 modules)
Subsystem-Level Plans: Major component decisions (spawned via subplan_parallel_spawn for independent subsystems)
- "Phase 1: Convert utility libraries (no external deps)"
- Each subsystem plan gets its own bounded context and inherits parent invariants
Module-Level Plans: Individual module conversions
- "Convert string_utils module"
- Context: Only the 47 functions and 12 dependent files
- Decision: "Use Rust's String type"
File-Level Plans: Specific file changes
- Actual code transformations
- Minimal context needed

At each level, only the relevant context is loaded. The persistent decision graph means we can always reconstruct why we're converting a particular module and what constraints (including inherited invariants) apply from higher-level decisions.

Child Plan Spawning Mechanism

In the actor definition for the execution actor, tool nodes can directly invoke registered tools to trigger child plans. The local/create-subplan tool is independently registered and referenced by name in the actor graph node. During execution, subplan_spawn decisions are realized as actual child plans, and subplan_parallel_spawn groups trigger concurrent spawning of all enclosed child plans.

# Example: Execution actor with subplan spawning capability.
# The graph uses a tool node referencing a named registered tool.
actors:
  code_executor:
    type: graph
    config:
      actor: anthropic/claude-3-opus
    skills:
      - local/plan-tools          # Skill containing create_subplan for LLM tool-calling
      - local/file-ops
    routes:
      execute_workflow:
        nodes:
          - name: spawn_test_subplan
            type: tool
            tool: local/create-subplan   # Named tool from Tool Registry

The local/create-subplan tool is independently registered via its own YAML configuration file:

# File: tools/create-subplan.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/create-subplan
  description: "Spawn a subplan for a given action"
  source: custom

  input_schema:
    type: object
    properties:
      action: { type: string }
      target_files: { type: array, items: { type: string } }
    required: [action]

  capability:
    writes: true
    checkpointable: false
    side_effects: [spawn_subplan]

  code: |
    subplan = ctx.spawn_subplan(
        action=params["action"],
        target_files=params.get("target_files", [])
    )
    return {"subplan_id": subplan.id}

The local/plan-tools skill references this tool (and others) by name:

# File: skills/plan-tools.yaml
skill:
  name: local/plan-tools
  description: "Tools for spawning and managing subplans"
  tools:
    - local/create-subplan

Child Plan Execution Modes

Sequential: Individual subplan_spawn decisions without a subplan_parallel_spawn wrapper execute one after another. If one fails, subsequent child plans are not started.
Parallel: Multiple subplan_spawn decisions grouped under a subplan_parallel_spawn decision execute concurrently. If one fails, others can continue. The subplan_parallel_spawn decision acts as a container that signals the system to spawn all enclosed child plans simultaneously.

Child Plan Failure Handling

Parallel execution (via subplan_parallel_spawn): Other parallel child plans continue even if one fails.
Sequential execution: Subsequent child plans are not started if a prior one fails.
Note: An "error" only occurs if an exception is thrown by the application (a bug). Plan failures (e.g., tests don't pass) are handled within the plan's logic, not as application errors.

Child Plan Result Merging

The way child plan results are merged depends on the resource type:

Git-compatible resources (source code, text files): Git-style merge
Databases: Transaction coordination or sequential application
Other resources: Pluggable merge strategies based on resource type
Non-mergeable resources: May require sequential execution only

The Plan "Decision Tree" and Visualization

CleverAgents intends to record enough information to render:

an ASCII tree in the TUI, and
optionally a GUI tree via visualization tools (D3/Cytoscape) once the data exists.

This implies each plan should persist:

decisions made,
the rationale (or at least the prompt/context snapshot that produced it),
dependencies ("this decision influenced these child plans").

This is required for "correcting plans" (see Behavior section).

Decision Data Model

Relationship Between Plan Description and Decisions

Each plan has a description field (inherited from the action's description, potentially with argument substitutions). This description acts as the primary component of the prompt fed to the strategy actor during the Strategize phase.

Decisions are choices that are NOT explicitly defined by the plan description. They represent the gaps, ambiguities, or implementation details that must be resolved to execute the plan.

For example:

Plan description: "Increase test coverage to 85%"
Decisions that emerge:
- "Which modules should be prioritized?" (not specified in description)
- "Should we use mocks or integration tests for the database layer?" (not specified)
- "Should we refactor the auth module to make it more testable, or write tests around it as-is?" (not specified)

Decision Making Based on Autonomy Level

Who makes decisions depends on the plan's automation level:

Automation Level	Who Makes Decisions
Manual	User is prompted for each decision point
Review-before-apply	Actor makes decisions automatically during Strategize, user reviews before Apply
Full automation	Actor makes all decisions automatically

When automation allows automatic decisions, the strategy actor uses its best judgment based on context, and records its reasoning in the decision's rationale field.

When user input is required, the system pauses and prompts the user:

Decision required: Which modules should be prioritized for test coverage?

Options identified by the strategy actor:
  1. auth module (currently 45% coverage, high risk)
  2. payment module (currently 52% coverage, high risk)  
  3. user module (currently 71% coverage, medium risk)

Your choice (or provide custom guidance): _

The Prompt as the Root Decision

The prompt passed to the strategize actor is itself a decision node in the decision tree—specifically, it's the root decision of type prompt_definition.

This is important because:

Every plan has its own prompt: The root plan's prompt comes from the action description + user arguments. Child plan prompts are created by parent plans during their execution.
Parent plans create child plan prompts: When a parent plan spawns a child plan, it decides what prompt to give that child plan. This is recorded as a prompt_definition decision in the parent's tree, and becomes the root decision of the child plan's tree.
Invariants flow into the decision tree: During Strategize, applicable invariants (from global, project, action, and plan scopes) are reconciled via the Invariant Reconciliation Actor and recorded as invariant_enforced decisions, making them explicit constraints that influence downstream decisions and child plans.
Unified correction mechanism: Since the prompt, invariants, and all other decisions are part of the same tree, correcting any of them uses the same agents plan correct command.

Plan: 01KH29QDEE6DZTXKWNKCV8VP0F
├── [prompt_definition] "Increase test coverage to 85% for the whole project."
├── [invariant_enforced] "Prioritize all functionality related to financial transactions and user management"
├── [invariant_enforced] "All API calls over TCP must be mocked"
├── [strategy_choice] "Prioritize auth and payment modules, implement them in parallel before the rest"
├── [subplan_parallel_spawn] "Implement auth and payment modules, in parallel"
│   ├── [subplan_spawn] "Write tests for auth module"
│   │   └── Plan: 01KH29R8WPKPBHRY7Q0NA9XW86
│   │       ├── [prompt_definition] "Write unit tests for auth module using mocks for the remote API calls"
│   │       ├── [implementation_choice] "Test login flow first"
│   │       └── ...
│   └── [subplan_spawn] "Write tests for payment module"
│       └── Plan: 01KH29RN2YKSXMTBDG82AKRHRA
│           ├── [prompt_definition] "Write unit tests for payment module using"
│           └── ...
└── [subplan_parallel_spawn] "Write tests for all modules except the auth and payment modules"
    └──  ...

Correcting Decisions (Including Prompts)

All corrections use the same unified command:

agents plan correct <decision_id> --mode=<mode> --guidance "<corrected decision text>"

Parameters:

<decision_id>: The ULID of the decision to correct
--mode: Either revert (rollback and re-run) or append (add fix at end)
--guidance: Free-form text specifying what the correct decision should be

Examples:

# Correct a strategy choice
agents plan correct 01ARZ3NDEKTSV4RRFFQ69G5FAV --mode=revert \
  --guidance "Prioritize the payment module first, not auth, due to upcoming deadline"

# Correct the root prompt to be more specific
agents plan tree <plan_id>
# Shows: [prompt_definition] id=01ARZ3NDEKTSV4RRFFQ69G5FAV "Increase test coverage to 85%"

agents plan correct 01ARZ3NDEKTSV4RRFFQ69G5FAV --mode=revert \
  --guidance "Increase test coverage to 85%, prioritizing auth and payment modules. Use mocks for database tests, not integration tests."

# Correct a subplan's prompt (originally created by parent plan)
agents plan correct 01BRZ4PDFLUTW5SSGR70H6GBW --mode=revert \
  --guidance "Write unit tests for auth module, focusing on edge cases for token expiration"

# Append a fix rather than rewriting history
agents plan correct 01ARZ3NDEKTSV4RRFFQ69G5FAV --mode=append \
  --guidance "The previous approach missed error handling tests - add comprehensive error path coverage"

# Remove an invariant that shouldn't apply
agents plan correct 01CRZ5QEHMVUX6TTHR81I7HCX --mode=revert \
  --guidance "Remove this invariant - TCP mocking is not needed for this module since it has no network calls"

# Add a missing invariant to the plan
agents invariant add --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J "All database queries must use parameterized statements"

Note: CLI commands should not require interactive input. The --guidance parameter provides the correction inline.

When to correct the prompt vs. a specific decision:

Situation	Correction Approach
Original request was too vague	Correct the `prompt_definition` decision
Strategy actor made a bad choice on a specific question	Correct that specific decision
Parent plan gave a child plan a bad prompt	Correct the child plan's `prompt_definition`
An invariant should not apply to this plan	Correct (remove) the `invariant_enforced` decision
A missing constraint should be added	Add a new `invariant_enforced` decision via `agents invariant add --plan` or correct the plan's strategy
Sequential child plans should run in parallel	Correct the relevant decisions to use a `subplan_parallel_spawn` grouping

Because the prompt is part of the decision tree, the system automatically knows that correcting it invalidates all downstream decisions in that plan (and its child plans).

Decisions are only created during the Strategize phase. The decision tree captures what choices were made and why, enabling correction and replay.

Decision Record Structure

Decision:
  # Identity
  decision_id: ULID                    # Unique identifier
  plan_id: ULID                        # Parent plan this decision belongs to
  parent_decision_id: ULID | null      # Parent decision (for tree structure)
  sequence_number: int                 # Order within the plan's decisions
  
  # Classification
  decision_type: enum
    - prompt_definition         # The prompt/description for this plan (root decision)
    - invariant_enforced        # An invariant (from global, project, action, or plan scope) applicable to this plan, added as a constraint
    - strategy_choice           # High-level approach decision during Strategize
    - implementation_choice     # How to implement a specific task
    - resource_selection        # Which resources to read/modify
    - subplan_spawn             # Decision to create a child plan (spawned later in Execute)
    - subplan_parallel_spawn    # Decision to spawn a group of child plans in parallel (contains subplan_spawn children)
    - tool_invocation           # Which skill/tool to use
    - error_recovery            # How to handle a failure
    - validation_response       # Response to validation failure
    - user_intervention         # User provided guidance/correction
  
  # The Decision Itself
  question: str                        # What question was being answered
  chosen_option: str                   # What was decided
  alternatives_considered: list[str]   # Other options that were evaluated
  confidence_score: float | null       # 0.0-1.0 if the actor provided confidence
  
  # Context Snapshot (for replay)
  context_snapshot:
    hot_context_hash: str              # Cryptographic hash of the exact context
    hot_context_ref: str               # Pointer to the full stored snapshot
    relevant_resources: list[ResourceRef]  # Every file/symbol that influenced this decision
    actor_state_ref: str               # Complete LangGraph checkpoint
    
  # When the system decides "refactor the authentication module to use async patterns," 
  # it permanently records:
  # - Which files were examined to make that decision
  # - What symbols and dependencies were traced
  # - The exact code state that was analyzed
  # - The reasoning chain that led to this choice
  # - Alternative approaches that were considered but rejected
  
  # Rationale
  rationale: str                       # Why this option was chosen
  actor_reasoning: str | null          # Raw LLM reasoning if available
  
  # Downstream Impact (populated during Execute phase)
  downstream_decision_ids: list[ULID]  # Decisions that depend on this one
  downstream_plan_ids: list[ULID]      # Child plans spawned because of this decision
  artifacts_produced: list[ArtifactRef] # Files/outputs created under this decision
  
  # Timestamps
  created_at: datetime
  
  # Correction Metadata
  is_correction: bool                  # Was this decision a correction of another?
  corrects_decision_id: ULID | null    # If correction, which decision was replaced
  correction_reason: str | null        # Why the correction was made
  superseded_by: ULID | null           # If this decision was later corrected

Decision Timing

Phase	Decision Activity
Strategize	Decisions are created, including `invariant_enforced` decisions for applicable invariants, `subplan_spawn` decisions, and `subplan_parallel_spawn` decisions grouping parallel child plans. `downstream_plan_ids` is empty.
Execute	Child plans are spawned. `downstream_plan_ids` is populated when child plans are created based on `subplan_spawn` decisions (both standalone and those within `subplan_parallel_spawn` groups).
Apply	No new decisions. History can be flagged for cleanup after successful apply.

Decision Tree Storage Schema

-- Core decision table
CREATE TABLE decisions (
    decision_id TEXT PRIMARY KEY,      -- ULID
    plan_id TEXT NOT NULL,
    parent_decision_id TEXT,
    sequence_number INTEGER NOT NULL,
    decision_type TEXT NOT NULL,        -- prompt_definition, invariant_enforced, strategy_choice,
                                       -- implementation_choice, resource_selection, subplan_spawn,
                                       -- subplan_parallel_spawn, tool_invocation, error_recovery,
                                       -- validation_response, user_intervention
    question TEXT,
    chosen_option TEXT NOT NULL,
    alternatives_considered TEXT,      -- JSON array
    confidence_score REAL,
    rationale TEXT,
    actor_reasoning TEXT,
    context_snapshot TEXT NOT NULL,    -- JSON blob
    is_correction BOOLEAN DEFAULT FALSE,
    corrects_decision_id TEXT,
    correction_reason TEXT,
    superseded_by TEXT,
    created_at TEXT NOT NULL,
    
    FOREIGN KEY (plan_id) REFERENCES plans(plan_id),
    FOREIGN KEY (parent_decision_id) REFERENCES decisions(decision_id),
    FOREIGN KEY (corrects_decision_id) REFERENCES decisions(decision_id),
    FOREIGN KEY (superseded_by) REFERENCES decisions(decision_id)
);

-- Downstream relationships (many-to-many for DAG)
CREATE TABLE decision_dependencies (
    upstream_decision_id TEXT NOT NULL,
    downstream_decision_id TEXT NOT NULL,
    dependency_type TEXT NOT NULL,     -- 'decision', 'plan', 'artifact'
    downstream_ref TEXT NOT NULL,      -- The actual ID of decision/plan/artifact
    
    PRIMARY KEY (upstream_decision_id, downstream_decision_id, downstream_ref),
    FOREIGN KEY (upstream_decision_id) REFERENCES decisions(decision_id)
);

-- Correction history
CREATE TABLE correction_attempts (
    attempt_id TEXT PRIMARY KEY,       -- ULID
    plan_id TEXT NOT NULL,
    original_decision_id TEXT NOT NULL,
    new_decision_id TEXT,
    original_subtree_snapshot TEXT,    -- Reference to archived state
    correction_reason TEXT,
    status TEXT NOT NULL,              -- 'pending', 'executing', 'completed', 'failed'
    created_at TEXT NOT NULL,
    completed_at TEXT,
    
    FOREIGN KEY (plan_id) REFERENCES plans(plan_id),
    FOREIGN KEY (original_decision_id) REFERENCES decisions(decision_id),
    FOREIGN KEY (new_decision_id) REFERENCES decisions(decision_id)
);

Action

What an Action Is

An action is a reusable plan template that is not associated with any projects yet.

Important: Actions are created via CLI commands, NOT YAML configuration files. YAML configuration files are only used to define actors.

Examples:

"Increase test coverage to 80%"
"Refactor module X to be async-safe"
"Write an RFC for feature Y"
"Provision an infra cluster and validate access" (non-code)

Actions are intentionally project-agnostic so they can be reused across projects.

An action is the first stage of a plan — before it is used. Because of this, invariants can be attached to actions. When an action is used (via agents plan use), any invariants attached to the action are carried forward as plan-level invariants on the resulting plan. This allows teams to bake constraints directly into reusable templates. Invariants can also be added to a plan after the action is used, via agents invariant add --plan or --invariant flags on agents plan use.

Action Creation (CLI)

Actions are created using the CLI:

agents action create \
  --name "local/code-coverage" \
  --description "Increase test coverage to target percentage" \
  --strategy-actor "local/coverage-strategist" \
  --execution-actor "local/coverage-executor" \
  --definition-of-done "Coverage reaches target percentage; All new tests pass" \
  --arg "target_coverage_percent:int:required:Target coverage percentage (0-100)" \
  --arg "test_framework:str:optional:Test framework to use (pytest, unittest, etc.)" \
  --invariant "Test files must not import production secrets" \
  --invariant "Coverage must not decrease for existing modules" \
  --invariant-actor "local/coverage-reconciler"

Required parameters:

--name: Namespaced name (e.g., local/code-coverage, myorg/deploy-action)
--strategy-actor: Name of the actor to use for Strategize phase
--execution-actor: Name of the actor to use for Execute phase
--definition-of-done: Free-form text describing completion criteria

Optional parameters:

--description: Human-readable description
--arg: Argument definitions (can be repeated). Format: name:type:required|optional:description
--invariant: Invariant to attach to this action (can be repeated). These are carried forward as plan-level invariants when the action is used.
--invariant-actor: Invariant Reconciliation Actor for plans created from this action. Can be overridden at use time via agents plan use --invariant-actor.
--reusable: Whether action remains available after use (default: true)
--read-only: Whether action only performs read operations (default: false)

Arguments defined with --arg are values that will be:

Injected into the description and/or definition of done (via templating)
Passed into the context of the actors
Required when using the action on projects

Action Data Model (Expanded)

A plan in the Action phase has:

1) `name` (namespaced)

Format:

[server:][namespace/]<name>

Rules:

If server is omitted, default server is assumed unless namespace is local.
If namespace is omitted, default is local.
Names should be stable identifiers (kebab-case recommended).

Examples:

local/code-coverage
myusername/code-coverage
myorgname/code-coverage
prod:myorgname/code-coverage (server-qualified)

2) `short_description`

Optional at creation; auto-filled if blank.

3) `long_description`

Optional but recommended for reusable actions.

4) `definition_of_done` (DoD)

Required. Must be explicit and testable.

5) `actors`

Two actors minimum, two optional:

strategy_actor (planner/architect) — required
execution_actor (builder/implementer) — required
estimation_actor (cost/risk estimator) — optional
invariant_actor (Invariant Reconciliation Actor) — optional; resolves invariant conflicts when the plan enters Strategize. Lookup falls back to project, then global config.

Actors can be:

an LLM agent (built-in),
a graph (custom yaml, or built-in),

Note: graphs are hierarchical allowing them to reference other actors as nodes.

Actor abstraction is central: an actor may be a single agent or an entire graph.

6) `reusable` (boolean)

Default: true.
If true: using the action creates a new plan in Strategize while leaving the action available.
If false: action self-deletes (or auto-archives) after first use.

7) `read_only` (boolean)

Default: false.
If true: the plan must only use read-only tools (tools with read_only: true in their capability metadata) and must never modify resources (even in sandbox).
Read-only actions are still useful for "investigation reports," architecture reviews, or dry-run planning.

8) `inputs_schema` (recommended addition)

To make actions genuinely reusable, actions should declare their inputs:

required args (e.g., target coverage percent),
optional args (e.g., test framework),
validation rules (types, bounds).

Example:

target_coverage_percent: integer 0–100

9) `safety_profile` (recommended addition)

A policy bundle that can be applied to enforce safe execution:

allowed skill categories,
require checkpoints,
require sandbox,
require human approval at Apply.

This relates to the "checkpointable tools + sandbox" approach for safe writing.

Strategy (Strategize Phase)

Using an Action (Transition to Strategize)

The use command transitions an Action into the Strategize phase by applying it to one or more projects:

# Basic usage
agents plan use local/code-coverage --project my-api-service

# Multiple projects
agents plan use local/schema-update \
  --project api-service \
  --project web-frontend \
  --project mobile-app

# With action arguments
agents plan use local/code-coverage \
  --project my-api-service \
  --arg target_coverage_percent=85 \
  --arg test_framework=pytest

# With explicit automation level
agents plan use local/deploy-action \
  --project staging-env \
  --automation-level manual

# With invariants attached at use time
agents plan use local/code-coverage \
  --project my-api-service \
  --arg target_coverage_percent=85 \
  --invariant "All API calls over TCP must be mocked" \
  --invariant "Do not modify the payments module"

Parameters:

--project: Project to apply the action to (can be repeated for multi-project plans)
--arg: Action argument values (format: name=value)
--automation-level: Override automation level for this plan
--invariant: Invariant to attach to the created plan (can be repeated). These are added as plan-level invariants in addition to any inherited from the action, project, or global scope.

When the action is used:

A new plan is created with a unique ULID
The plan's automation level is determined (plan > session > global)
Any invariants from the action are carried forward as plan-level invariants, combined with any --invariant flags provided
The plan enters the Strategize phase
The Invariant Reconciliation Actor computes the effective invariant view (resolving conflicts using plan > project > global precedence)
The strategy_actor begins analyzing the project(s)

What Strategize Does

When an action is used on projects, it becomes a plan in Strategize.

Strategize is:

read-only, producing a plan of attack,
responsible for gathering context from project resources,
responsible for collecting applicable invariants (from global, project, action, and plan scopes), computing the effective invariant view via the Invariant Reconciliation Actor (applying plan > project > global precedence), and recording them as invariant_enforced decisions,
responsible for generating a strategy and child plan blueprint (using subplan_spawn and subplan_parallel_spawn decisions),
not allowed to execute child plans or modify resources.

This "architect vs coder" separation is explicitly described as a core motivation.

Resource-aware dependency analysis: During the Strategize phase, the strategy actor employs specialized mechanisms to compute precise dependency closures:

# Pseudocode of what happens inside a strategy actor
def compute_closure_for_refactoring(target_module):
    closure = ResourceClosure()
    
    # Direct file dependencies
    closure.add_files(find_imports(target_module))
    closure.add_files(find_includes(target_module))
    
    # Symbol dependencies
    for symbol in extract_exported_symbols(target_module):
        closure.add_files(find_symbol_usage(symbol, scope='project'))
    
    # Test dependencies
    closure.add_files(find_tests_for_module(target_module))
    
    # Build system dependencies
    closure.add_files(find_build_references(target_module))
    
    return closure

The system leverages several key insights:

Modular boundaries exist: Even in legacy codebases, there are natural boundaries
Changes are incremental: We don't convert 50,000 files atomically
Dependencies are sparse: Most modules depend on a small fraction of the codebase
Interfaces are narrow: Public APIs are much smaller than implementations

Strategize Data Model

A plan in Strategize contains all Action fields plus:

1) `projects`

A list of projects the plan is used on.

Important: A strategy plan may target multiple projects. Multi-project work in one "window" is considered a major usability advantage over tools that require being run from a single directory.

2) `strategy_context`

A structured object describing:

what resources were considered,
how they were retrieved,
what filtering/limits were applied,
what the actor saw.

This matters because a plan must be debuggable and correctable later.

Recommended fields:

resource_refs: IDs of resources used
queries: search queries performed
selected_chunks: chunk IDs + sources + reasons
constraints: context window limits, file ignore patterns
generated_summaries: if summarization occurred

3) `strategy`

The output plan:

steps (ordered and/or DAG),
conditions/branches ("if tests fail, do X"),
child plans to spawn (including which action templates to use, and whether they should run in parallel via subplan_parallel_spawn),
evaluation criteria (how to know success),
risk assessment.

4) `execution_blueprint` (recommended addition)

Strategize should output not only narrative text but also a machine-usable blueprint:

list of tasks,
required skills,
expected outputs,
dependencies between tasks.

This blueprint becomes the input to Execute.

5) `cost_estimate` and `risk_estimate` (optional)

Cost and risk estimation is optional but recommended for production use.

When enabled, a specialized estimation actor analyzes:

The initial prompt/request
The strategy produced by the Strategize phase
Historical data from similar plans (if available)

And produces estimates for:

LLM tokens/cost range
Number of steps/child plans expected
Expected risk of rollbacks
Estimated execution time

Implementation: Similar to how there's a strategy_actor and execution_actor for each action, there can be an optional estimation_actor whose entire job is cost/risk estimation. This actor runs after Strategize completes (before Execute) and its output is informational only.

# Example: Action with estimation actor
agents action create \
  --name "local/expensive-refactor" \
  --strategy-actor "local/refactor-planner" \
  --execution-actor "local/refactor-executor" \
  --estimation-actor "local/cost-estimator" \
  --definition-of-done "All code refactored according to plan"

This becomes critical in server/multi-user usage and cost controls.

Execution (Execute Phase)

What Execute Does

Execute is where the plan actually performs work, but in a sandboxed environment that can later be reviewed and applied.

Key properties:

Work happens in a sandbox All file modifications, generated artifacts, and intermediate outputs live in an isolated "execution workspace" until Apply.
Execute may spawn child plans Child plan spawning is a first-class behavior of Execute: a parent plan can distribute work to child plans (sequentially via subplan_spawn or concurrently via subplan_parallel_spawn) and merge results.
Execute must support checkpointing / rollback (when enabled) Checkpointable tools allow rolling back to a checkpoint ID to recover from partial failure or wrong turns.
Execute produces a "reviewable diff" Diff review sandbox is described as a differentiating feature: users can inspect changes before applying.

Execution Workspace / Sandbox Model (Detailed)

A sandbox isolates plan execution from the real project resources until Apply.

Key Sandbox Principles

Lazy Sandboxing: Resources are sandboxed only when accessed, not upfront.
- A project may have many resources (git repo + 10 databases + cloud accounts)
- A plan may only modify one resource
- Only accessed resources are sandboxed
- Efficient for large projects
Per-Plan Sandboxes: Each plan and child plan has its own sandbox containing only the resources it edits.
Resource-Defined Strategy: The sandbox strategy is defined on each resource, not by skills or globally.
Cleanup Behavior:
- Sandboxes are cleaned up before application exit when possible
- Abandoned sandboxes (from crashes, etc.) are cleaned up on next application run
- Completed plan sandboxes are cleaned or archived based on retention policy

Sandbox Implementation Strategies

Different resource types require different sandbox strategies:

Resource Type	Strategy	Rollback Mechanism
`git-checkout`	`git_worktree`	Git reset/checkout
`git`	`none`	N/A (represents a repo instance — not directly sandboxable)
`fs-mount`	`copy_on_write` or `overlay`	Restore from snapshot
`fs-directory`	`copy_on_write`	Restore from snapshot
Custom database types	`transaction_rollback`	Transaction rollback
Custom API types	`none`	Often not sandboxable

1. Git worktree / branch sandbox (preferred for code)

Create a worktree or temporary branch
All modifications are commits or staged changes
Apply merges/cherry-picks

Pros: natural rollback, diff support, efficient Cons: requires git

2. Filesystem copy sandbox

Copy project directory to a sandbox directory
Execute modifies sandbox copy
Apply syncs diff back

Pros: simple Cons: expensive for huge repos

3. Overlay filesystem sandbox

Use overlayfs-style "copy-on-write" to avoid full copies

Pros: efficient Cons: more complex, OS-dependent

4. Transaction-based sandbox (for databases)

Begin transaction at sandbox creation
All operations within transaction
Rollback on failure, commit on apply

Pros: native to databases Cons: long-running transactions can cause issues

5. No sandbox (for non-sandboxable resources)

Some resources cannot be sandboxed (certain APIs, cloud services)
User proceeds at their own risk
Plan should warn about non-sandboxable resources

Multi-Resource Sandboxing

When a plan accesses multiple resources:

Each resource gets its own sandbox (based on its defined strategy)
Sandboxes are independent
Apply commits each sandbox separately
If any sandbox Apply fails, others may still succeed (partial apply)

Complete isolation during execution prevents compound errors: Each plan executes in its own sandbox, which means:

Plan A (refactoring auth module):
- Sandbox A1: Contains only auth/*.cpp, auth_tests/*.cpp
- Cannot see Plan B's intermediate states
- Cannot accidentally depend on Plan B's half-done work

Plan B (updating API endpoints):
- Sandbox B1: Contains only api/*.cpp, api_tests/*.cpp  
- Makes changes assuming current auth interface
- Protected from Plan A's intermediate refactoring

Hierarchical merge resolution: When child plans complete, the parent plan performs intelligent merging:

def merge_subplan_results(subplan_results):
    # Group by resource type
    by_resource = group_by_resource_type(subplan_results)
    
    # Apply resource-specific merge strategies
    for resource_type, changes in by_resource:
        if resource_type == 'git-checkout':
            merge_git_changes(changes)  # Three-way merge
        elif resource_type == 'fs-mount':
            merge_fs_changes(changes)   # Copy-on-write reconciliation
        elif resource_type.startswith('database'):
            merge_db_changes(changes)   # Sequential application
    
    # Validate merged state
    run_integration_tests()

Execution Data Model

A plan in Execute contains:

1) `execution_context`

The context used for execution (often smaller/more tactical than strategy context).

2) `execution_log`

Structured timeline of:

tool calls (with parent skill noted),
actor calls,
outputs,
errors and retries,
checkpoints created.

This log is essential for debugging.

3) `artifacts`

Outputs produced:

changed files,
generated files,
reports,
diagrams,
test outputs,
diffs.

4) `sandbox_ref`

Pointer to the sandbox location/state:

path, branch name, workspace ID, container ID, etc.

5) `checkpoint_graph` (if enabled)

A record of checkpoints:

checkpoint ID
timestamp
tool responsible (and its parent skill)
resources affected
rollback instructions / metadata

Checkpointing in Execute (Core Safety Mechanism)

The intended user-level behavior is:

"Give me a checkpoint ID."
Perform additional operations.
"Roll back to checkpoint X."

Not all tools can support this; checkpointing must be declared per tool (in its capability metadata).

Tool-level checkpointability

Each tool declares (via its capability metadata):

checkpointable: true|false
checkpoint_scope: what granularity of rollback is supported (file, transaction, commit, snapshot)
rollback_mechanism: how rollback occurs

Examples:

File tools (from a file-ops skill): snapshot file states pre-modification
Git tools (from a git-ops skill): create commit or stash; rollback is reset/checkout
Shell/CLI tools (running inside a container): rollback by restoring filesystem snapshot or reloading base image state

It should be noted that checkpointing is easier when tool scope is constrained (e.g., "only files within a docker image + git").

Plan-level rollback policy

Plans should have an option:

rollback_enabled: true|false

If disabled, the plan may use more generic/unsafe tools with fewer restrictions (useful for low-stakes tasks).

Execution as Transactions (Recommended)

Execution should be treated like a transactional pipeline:

Each step either:
- commits a checkpoint on success, or
- rolls back to the previous checkpoint on failure.

This is explicitly motivated by "partial failure leaves codebase inconsistent" and the need for transaction rollback.

Tool-Based Resource Modification (Modern Architecture)

IMPORTANT: CleverAgents does NOT parse LLM output to extract code. Instead, it uses the modern tool-based approach pioneered by Claude Code, Cursor, and Aider where:

LLMs call tools directly (edit_file(), write_file(), delete_file(), etc.) — tools provided by referenced skills
Tools operate on the sandbox - each tool invocation modifies sandbox state directly
ChangeSet is built from tool invocations - not by parsing LLM text output
Validation runs on sandbox state - after tools execute, not on parsed output

This architecture provides:

Atomic operations: Each tool call is a discrete, trackable change
No parsing ambiguity: Tools have structured parameters (path, content, etc.)
Resource-agnostic: Same pattern works for files, databases, APIs, any resource type
Safety by design: Tools run in sandbox with defined capabilities and restrictions
MCP compatibility: Tools from MCP-based skills map directly to MCP tools for external integrations

How It Works

sequenceDiagram
    participant LLM as LLM Agent
    participant Router as Tool Router
    participant Sandbox as Sandbox
    participant CS as ChangeSet
    participant Val as Validator

    LLM->>Router: Tool call (with parameters)
    Router->>Router: Validate parameters
    Router->>Router: Enforce capability restrictions
    Router->>Sandbox: Execute tool in sandbox
    Sandbox->>Sandbox: Operate on sandboxed state
    Sandbox->>Sandbox: Record invocation
    Sandbox->>Sandbox: Create checkpoint (if needed)
    Sandbox->>CS: Emit Change record
    CS->>CS: Accumulate into ChangeSet
    CS->>Val: Submit for validation
    Val->>Val: Run validators on sandbox state
    Val->>Val: Generate diff from ChangeSet
    Val-->>LLM: Present for review before Apply

Built-in Resource Tools

CleverAgents provides these core tools (via built-in skills) for resource manipulation:

Tool	Description	Creates Change?
`read_file(path)`	Read file contents	No
`write_file(path, content)`	Create/overwrite file	Yes
`edit_file(path, changes)`	Apply targeted edits	Yes
`delete_file(path)`	Remove file	Yes
`move_file(src, dst)`	Rename/move file	Yes
`create_directory(path)`	Create directory	Yes
`list_files(pattern)`	List files matching glob	No
`search_files(pattern, content)`	Search file contents	No
`get_file_info(path)`	Get file metadata	No

Each built-in tool automatically:

Operates within sandbox boundaries
Records changes to the ChangeSet
Validates parameters against project configuration
Enforces deny-list patterns (.git/, node_modules/, etc.)

Why Not Parse LLM Output?

The obsolete approach of parsing markdown code fences has fundamental problems:

Ambiguity: Is text explanation or code? Where does one file end and another begin?
Fragility: Models output varying formats; regex parsing is brittle
Loss of semantics: You lose the intent (create vs modify vs delete)
No atomicity: Can't rollback individual operations
Resource-limited: Only works for files, not databases or other resources

The tool-based approach solves all of these by making each operation explicit, typed, and trackable.

Semantic Error Prevention

CleverAgents provides multiple layers of proactive error prevention that catch semantic errors before they can propagate through the system.

Layer 1: Decision-time Validation During Strategize

Every decision includes semantic validation:

Decision: Refactor payment module to async
alternatives_considered:
  - "Convert to async/await patterns" (chosen)
  - "Use thread pool with channels" (rejected: doesn't integrate with async ecosystem)
  - "Keep synchronous with timeout" (rejected: doesn't solve core latency issue)
confidence_score: 0.85
validation_performed:
  - Checked all payment API consumers can handle async
  - Verified database driver supports async operations
  - Confirmed no regulatory requirement for sync processing

Layer 2: Execution-time Semantic Guards

The execution actor uses a tool node that references the independently registered local/validate-api-compat tool:

# Actor graph uses a named tool node for semantic validation
actors:
  code_executor:
    type: graph
    skills:
      - local/semantic-validators    # Skill containing validation tools for LLM tool-calling
    nodes:
      - name: semantic_validator
        type: tool
        tool: local/validate-api-compat   # Named tool from Tool Registry

The local/validate-api-compat tool is independently registered via its own YAML:

# File: tools/validate-api-compat.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/validate-api-compat
  description: "Check for breaking API changes and attempt auto-migration"
  source: custom

  capability:
    writes: true
    checkpointable: true

  code: |
    # Not just syntax checking - semantic validation
    old_api = extract_api_signature(previous_version)
    new_api = extract_api_signature(current_version)
    
    breaking_changes = find_breaking_changes(old_api, new_api)
    if breaking_changes:
        affected_consumers = find_api_consumers(breaking_changes)
        migration_plan = generate_migration(breaking_changes)
        
        if can_auto_migrate(affected_consumers, migration_plan):
            apply_migration(migration_plan)
        else:
            raise SemanticError(
                "Breaking API changes require manual review",
                changes=breaking_changes,
                affected=affected_consumers
            )

The local/semantic-validators skill references this tool by name:

# File: skills/semantic-validators.yaml
skill:
  name: local/semantic-validators
  description: "Semantic validation tools for API compatibility and code invariants"
  tools:
    - local/validate-api-compat

Layer 3: Invariant Enforcement

Invariants are named constraints that guide and constrain plan execution. They can be attached at four scopes, all managed through the unified agents invariant command:

Global invariants: Apply to all plans across all projects. Added via agents invariant add --global.
Project invariants: Apply to all plans targeting a specific project. Added via agents invariant add --project. Can also be attached at creation time via agents project create --invariant.
Action invariants: Attached to an action and carried forward as plan-level invariants when the action is used. Added via agents invariant add --action. Can also be attached at creation time via agents action create --invariant.
Plan invariants: Apply to a specific plan and its child plans. Added via agents invariant add --plan. Can also be attached at creation time via agents plan use --invariant.

Precedence and conflict resolution: When invariants from different scopes conflict, narrower scopes override broader scopes:

Plan-level invariants override project-level and global-level invariants.
Project-level invariants override global-level invariants.

Conflict resolution is performed by the Invariant Reconciliation Actor — a dedicated actor responsible for comparing invariants across scopes, identifying conflicts, and producing the final effective invariant view for a plan. The Invariant Reconciliation Actor is set at three levels via --invariant-actor:

Global config: Set via agents config set invariant-actor <ACTOR>. Defines the default Invariant Reconciliation Actor used when neither the project nor the plan specifies one.
Project-level: Set via --invariant-actor on agents project create (or later via agents config set --project). If a project defines an Invariant Reconciliation Actor, it is used to reconcile that project's invariants against global invariants.
Plan-level: Set via --invariant-actor on agents action create (carried forward when the action is used) or agents plan use (which overrides whatever was set on the action). If a plan has an Invariant Reconciliation Actor, it reconciles invariants from all scopes (plan, project, and global) and produces the final effective view for that plan.

The lookup order is: plan → project → global config. The first Invariant Reconciliation Actor found is used.

Invariant view calculation: When an action is used and a plan enters the Strategize phase, the Invariant Reconciliation Actor computes the effective invariant view by:

Collecting all invariants from global, project, plan, and action scopes.
Identifying conflicts (invariants from different scopes that contradict each other).
Applying precedence rules (plan > project > global) to resolve conflicts.
Producing the final set of effective invariants.

Each effective invariant is then recorded as an invariant_enforced decision in the plan's decision tree. This makes invariants visible, auditable, and correctable through the standard decision correction mechanism.

Child plan inheritance: When a top-level plan spawns child plans, the parent's effective invariant view (already reconciled) is passed down to each child plan. Child plans do not re-run reconciliation — they inherit the parent's resolved view.

Correcting invariants: The correction mechanism for invariant_enforced decisions supports two operations:

Remove: Remove an existing invariant from the plan's decision tree (the invariant remains defined at its scope but is no longer enforced for this plan).
Add: Add a new invariant to the plan. When adding, the user can select from invariants already accessible to the plan (those defined at the plan, action, project, or global scope), or provide free-form text to create a new ad-hoc invariant.

# Add invariants at different scopes
agents invariant add --global "All public APIs must maintain backward compatibility"
agents invariant add --global "Payment processing must be idempotent"
agents invariant add --project local/api-service \
  "Database transactions must complete within 5 seconds"
agents invariant add --project local/api-service \
  "Authentication must always use OAuth2"
agents invariant add --plan <PLAN_ID> "All API calls over TCP must be mocked"
agents invariant add --action local/code-coverage "Test files must not import production secrets"

# List invariants
agents invariant list --global
agents invariant list --project local/api-service
agents invariant list --plan <PLAN_ID> --effective   # Shows reconciled view

# Remove an invariant
agents invariant remove <INVARIANT_ID>

# Attach invariants at creation time (convenience)
agents project create --name local/api-service --invariant "All endpoints must validate auth tokens"
agents action create local/code-coverage --invariant "Test files must not import production secrets" ...
agents plan use local/code-coverage --project local/api-service --invariant "Mock all network calls"

# Correct an invariant decision (remove or replace via standard correction)
agents plan correct <DECISION_ID> --mode=revert \
  --guidance "Remove this invariant - it does not apply to this module"

The system collects, reconciles, and checks invariants:

class InvariantEnforcer:
    def compute_effective_invariants(self, plan):
        """Compute the effective invariant view for a plan using the Invariant Reconciliation Actor."""
        # 1. Collect raw invariants from all scopes
        raw = self.collect_all_invariants(plan)
        
        # 2. Find the Invariant Reconciliation Actor (plan -> project -> global config)
        reconciler = (
            self.get_plan_invariant_actor(plan)
            or self.get_project_invariant_actor(plan)
            or self.get_global_invariant_actor()
        )
        
        # 3. Reconcile: apply precedence (plan > project > global), resolve conflicts
        effective = reconciler.reconcile(raw, precedence=['plan', 'project', 'global'])
        return effective
    
    def collect_all_invariants(self, plan):
        """Collect invariants from all scopes accessible to this plan."""
        invariants = []
        invariants.extend(self.get_global_invariants())
        for project in plan.projects:
            invariants.extend(self.get_project_invariants(project))
        invariants.extend(self.get_action_invariants(plan.action))
        invariants.extend(self.get_plan_invariants(plan))
        return invariants
    
    def check_invariant_preservation(self, changes, enforced_invariants):
        """Check that changes respect all enforced invariants."""
        for invariant in enforced_invariants:
            if not self.verify_invariant(invariant, changes):
                return InvariantViolation(invariant, changes)
        return Success()

Layer 4: Predictive Error Prevention

The system learns from past failures:

Error Pattern Database:
  - pattern: "Async conversion in payment module"
    historical_failures:
      - "Race condition in payment confirmation"
      - "Timeout handling breaks idempotency"
    preventive_checks:
      - "Add explicit transaction boundaries"
      - "Verify idempotency keys are preserved"
      - "Check distributed lock acquisition"

Applied (Apply Phase)

What Apply Does

Apply takes the sandboxed work product and makes it "real" in the project.

Core properties:

Apply is a controlled commit step Apply exists specifically to separate "generated work" from "committed work," enabling review and safer automation.
Apply is often the highest-risk step It changes real systems. This is where permissions, approvals, and checks matter most.
Apply produces a terminal 'applied' plan After successful apply, the plan becomes Applied.

Apply Responsibilities (Recommended Checklist)

Apply should perform (configurable) validations before committing:

Diff review gate
- If automation level requires review, show:
  - changed files summary,
  - full diff,
  - risk warnings.
Pre-apply tests
- Run validation as defined by the actor and/or project (see below).
Conflict resolution
- If applying to a git repo, handle rebase/merge conflicts safely.
Audit log
- Record who applied, what changed, when, and why.

Validation Configuration

Validation is defined by the actor configuration and project settings, not hardcoded.

Actor-defined validation: The execution actor's workflow should include validation nodes that:

Read project-defined test/validation commands from context
Execute appropriate tests based on resource type
Handle failures by iterating (attempting fixes) or escalating to user

Project-defined validation: Each project should define how its resources are validated:

# Example: Add validation configuration to a project
agents project set-validation \
  --project my-api-service \
  --resource api-repo \
  --test-command "pytest" \
  --lint-command "ruff check ." \
  --type-check-command "pyright"

This information is passed into the actor's context, allowing generic actors (not specific to any project) to execute appropriate validation.

Validation Failure Handling

When validation fails:

Iteration: Actor attempts to fix the issue (e.g., fix failing tests)
Retry limit: After several failed attempts, iteration stops
User intervention: User can provide additional instructions
Resume: Plan continues with new guidance

The user can prompt the plan with additional instructions when stuck:

agents plan prompt <plan_id> "Try using mock objects for the database tests"

Apply Data Model

A plan in Apply includes:

apply_summary
applied_artifacts (final commit hash, merged PR link, file list)
final_validation_results (test outputs, lint outputs)
approval_record (if human approvals are required)
deployment_record (optional, if apply triggers deploy)

"Applied" Terminal State

When Apply succeeds:

plan.phase = applied
plan.state = complete
the sandbox may be cleaned up or archived depending on retention policy

When Apply fails:

plan.phase remains Apply
plan.state = errored
sandbox remains intact for inspection/retry

Project

A project is the boundary that answers:

"Where is the work happening?"
"What can this plan read and write?"
"What skills (and their tools) can this plan use?"
"What context is available?"

A project is a collection of linked resources and configuration. Projects link to independently registered resources from the Resource Registry — they do not define resources inline. A resource can be linked to multiple projects, enabling shared resources across teams and workflows.

Important: Projects are created via CLI commands, NOT YAML configuration files.

Project Types: Local vs Remote

Projects are classified based on their resources:

Type	Definition	Where Plans Can Execute
Local	Contains at least one local-only resource	Client only
Remote	All resources are remotely accessible	Client or Server

This distinction matters for server mode: the server can only execute plans on remote projects because it needs network access to all resources.

Project Creation (CLI)

# Step 1: Register resources independently
agents resource add git-checkout local/api-repo \
  --path /repos/api-service \
  --branch main

agents resource add local/database local/staging-db \
  --connection-string "postgresql://staging.example.com/mydb" \
  --read-only

# Step 2: Create the project
agents project create \
  --name "my-api-service"

# Step 3: Link resources to the project
agents project link-resource \
  --project "my-api-service" \
  --resource local/api-repo

agents project link-resource \
  --project "my-api-service" \
  --resource local/staging-db \
  --read-only

Resources are registered once and can be linked to multiple projects. The resource's type, sandbox strategy, and capabilities are defined by its resource type in the Resource Registry — not by the project.

Project Data Model

A project includes:

1) Identity

project_id (ULID)
name
namespace (follows same rules as actors: local/, <username>/, <orgname>/)
is_remote (boolean, derived from resources)

2) Linked Resources

Resources are the "things you can act on." Projects link to independently registered resources from the Resource Registry rather than defining them inline. This means:

A resource can be linked to multiple projects (shared resources).
The resource's type, capabilities, sandbox strategy, and DAG relationships are defined by the resource itself — not by the project.
Projects can apply project-level overrides when linking (e.g., marking a writable resource as read-only within a specific project context).

Each linked resource reference has:

resource_name (reference to a Resource Registry entry)
project_read_only (boolean — project-level read-only override)
alias (optional short name for referencing within the project)

The full resource details (type, location, sandbox strategy, capabilities, parent/child DAG, etc.) are stored in the Resource Registry. See the Resources section for details.

3) Context configuration

Project-level defaults:

ignore patterns (like .gitignore semantics)
max file size
indexing strategy
preferred chunking/summarization policy (even if evolving)
context retention policy

4) Security / permissions defaults

who can run write plans
which skill categories are allowed or denied
whether apply requires approvals

Multi-Project Operations

A single plan may target multiple projects (e.g., updating shared schemas across services). This is considered a key UX advantage over "run in one directory" systems. Because resources are independently registered and can be linked to multiple projects, shared resources across projects are a natural part of the architecture.

In multi-project execution:

Strategize must clarify which steps affect which projects.
Execution must isolate sandboxes per project OR define a composite sandbox. When multiple projects share the same resource, a single sandbox for that resource is used.
Apply must commit changes to each project separately, with separate approval records if necessary.
Tool resource bindings are resolved per-project — the same tool may bind to different resources depending on which project context it runs in.

Namespaces

Namespaces define ownership, scoping, and discoverability of actors, tools, skills, resources, resource types, actions, projects, and plans.

All named entities use the format <namespace>/<name>.

Namespace Types

Namespace	Scope	Storage	Examples
`local/`	Current machine only	Local database	`local/my-reviewer`, `local/test-action`
`<username>/`	Personal server namespace	Server database	`freemo/code-analyzer`, `jsmith/deploy-script`
`<orgname>/`	Organization namespace	Server database	`cleverthis/standard-review`, `acme/deploy-action`
`openai/`, `anthropic/`, etc.	Built-in LLM actors	N/A (built-in)	`openai/gpt-4`, `anthropic/claude-3-opus`

Namespace Rules

local/
- Reserved namespace for local-only items
- Exists only on the current machine
- Stored in local database
- Fast iteration, no sharing
- Default namespace when none specified
<username>/ (e.g., freemo/, jsmith/)
- Personal namespace on the server
- Created when user registers an account
- Stored on server, synced when connected
- Used for reusable entities (actions, actors, tools, skills, resources) a user wants across machines
- Only the owning user can create/modify items
<orgname>/ (e.g., cleverthis/, acme/)
- Organization namespace on the server
- Created when organization is registered
- Shared across team members
- Permissions and approvals managed at org level
- All namespaced entities (actions, actors, tools, skills, resources, projects) can be centrally managed
Built-in Provider Namespaces (openai/, anthropic/, google/, etc.)
- Reserved for built-in LLM actors
- Automatically available when API keys are configured
- In server mode: available if logged in and server has keys
- In local mode: requires environment variables or app configuration
- Cannot be used for custom actors

Server-qualified Names

To disambiguate between servers (when connected to multiple):

dev:freemo/code-coverage (personal namespace on dev server)
prod:cleverthis/deploy-action (org namespace on prod server)

This enables a pattern where:

local machine runs a lightweight client
server stores canonical definitions
multiple servers can coexist

Actor

What an Actor Is

An actor is the abstraction that generalizes "agent" into "anything conversational."

It can be as small as a single LLM agent.
It can also be an entire graph that itself calls other actors/tools.
Actors can be nested/hierarchical, enabling "orchestrator of orchestrators."

Every custom actor IS a graph (a LangGraph defined via YAML configuration). Even a simple actor wrapping a single LLM is technically a graph with one node.

Actor Naming

Actors are always named using <namespace>/<name> format:

local/my-reviewer - Local actor
freemo/code-analyzer - Personal server actor
cleverthis/deploy-specialist - Organization actor
openai/gpt-4 - Built-in LLM actor

Actor Definition (YAML Configuration)

Actors are defined via YAML configuration files. Tools and skills are also defined via their own YAML configuration files. YAML configuration is used for actors, tools, and skills (not for actions or projects).

Example actor configuration (see examples/ directory for full examples):

cleveragents:
  version: "3.0"
  default_actor: workflow_controller

actors:
  # Simple LLM actor with skills referenced by name
  my_assistant:
    type: llm
    config:
      actor: openai/gpt-4           # Reference to built-in actor
      temperature: 0.7
      system_prompt: |
        You are a helpful assistant.
        Current task: {{ context.task_description }}
    skills:
      - local/file-ops               # Grants access to all tools in this skill
      - local/git-ops

  # LLM actor with a composite skill (includes many sub-skills)
  data_processor:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      system_prompt: |
        You are a data processing assistant.
    skills:
      - local/data-toolkit           # A skill containing analysis + transformation tools

  # Actor referencing another actor
  reviewer:
    type: llm
    config:
      actor: local/code-reviewer    # Reference to another custom actor
      memory_enabled: true
      max_history: 20
    skills:
      - local/file-ops
      - local/git-ops

routes:
  main_workflow:
    type: graph
    entry_point: start
    nodes:
      - name: analyze
        type: agent
        agent: my_assistant
      - name: process
        type: agent
        agent: data_processor
    edges:
      - source: start
        target: analyze
      - source: analyze
        target: process
      - source: process
        target: end

context:
  global:
    task_description: "Default task"

Actor Arguments

All actors can receive arguments when invoked, including built-in actors. Arguments are passed when:

An action is used on projects (arguments flow to strategy/execution actors)
An actor is directly invoked

Arguments are injected into the actor's context and can be used in Jinja2 templates within prompts.

For built-in actors (like openai/gpt-4), common arguments include:

temperature
max_tokens
system_prompt

Actor Composition (Hierarchical References)

Actors can reference other actors by name:

actors:
  complex_workflow:
    type: llm
    config:
      actor: local/base-analyzer    # References another actor

Load order matters: Referenced actors must be loaded/defined before actors that depend on them.

This enables hierarchical composition where:

Actor A's graph can include nodes that call Actor B (by name)
Actor B itself is a graph that might call Actor C
And so on...

Actor vs Agent (Relationship)

Agent: an actor that is specifically an LLM with tools and reasoning behaviors.
Actor: may be an agent, but may also be:
- a composite workflow,
- a multi-step graph,
- a wrapper around a third-party system (as long as it's "text in → text out" conversationally).

Actor Definition Fields (From Notes + Extended)

A robust actor schema should include:

name (namespaced)
provider (LLM provider or runtime target)
model
system_prompt (or prompt template)
skill_access_policy (which skill categories/names are allowed or denied)
graph_descriptor (for composite actors)
memory_policy (per-plan/per-actor—see memory section)
context_view_policy (what context this actor sees)
limits (token limits, tool call limits, retries)
cost_policy (caps, budgets)
metadata (use cases, version)

Actor Composition and Graphs

Actors can reference:

other actors (by namespaced name)
skills (by namespaced name — all tools from referenced skills become available)
subgraphs

This is central to enabling both:

multi-agent orchestration, and
modular reuse of workflows.

Nodes in the Graph: Actors and Tools

Graph nodes can be any of:

an actor (another LLM agent or composite workflow, referenced by name),
a tool node — a deterministic, non-LLM step that directly invokes a tool. Tool nodes can:
- Reference a named registered tool by its fully-qualified name (e.g., tool: local/run-migrations). The tool must be registered in the Tool Registry via agents tool add. Metadata can optionally be overridden at the point of use.
- Define an anonymous inline tool using the same format as a tool YAML body (with anonymous: true). This is useful for one-off, workflow-specific operations that don't warrant separate registration.

This is a powerful simplification: actors provide intelligence, tools provide capability (both as graph nodes and through skills for LLM tool-calling), and skills organize tools into reusable collections. Everything participates in the same graph.

Tool node with named tool reference:

nodes:
  - name: run_db_migrate
    type: tool
    tool: local/run-migrations          # Named tool from Tool Registry
    override:                           # Optional metadata override
      capability:
        human_approval_required: true

  - name: spawn_tests
    type: tool
    tool: local/create-subplan          # Another named tool

Tool node with anonymous inline tool:

nodes:
  - name: custom_validation
    type: tool
    anonymous: true
    description: "Validate output format before proceeding"
    input_schema:
      type: object
      properties:
        data: { type: object }
    capability:
      read_only: true
    code: |
      # Inline Python — same format as a named tool YAML body
      if not params["data"].get("status"):
          raise ValueError("Missing status field")
      return {"valid": True}

Agent

Agent Definition

In CleverAgents, an agent is a specialized actor with:

a conversational interface,
tool-calling capability,
potentially memory, planning heuristics, and role identity.

Examples of agent roles:

planner/architect (strategy actor)
coder/implementer (execution actor)
reviewer/qa agent
release/apply agent

The transcript explicitly discusses role separation like planner/coder/reviewer in context views/memory proposals.

Agent Behavior Configuration

Agents should be configurable without code changes:

prompt templates
tool sets
safety constraints
style constraints (verbosity, code style)
reliability controls (self-checks, validations)

A design goal is user empowerment: "users customize LLM behavior without modifying core code."

Tools

What a Tool Is

A tool is a namespaced, independently registered, callable operation. It is the atomic unit of execution in CleverAgents — the smallest piece of functionality that can read, write, or transform resources. Tools are defined in their own YAML configuration files, managed through the agents tool CLI commands, and registered in the Tool Registry.

Tools follow the same <namespace>/<name> naming convention as actors, skills, and other entities (e.g., local/run-migrations, cleverthis/validate-api, local/create-subplan). They support optional server-qualified prefixes for multi-server disambiguation (e.g., dev:freemo/custom-analysis).

The Dual Role of Tools

Tools serve two distinct roles in CleverAgents:

As components of a Skill: A skill references tools by name to assemble a reusable capability collection. When an actor references a skill, all of that skill's tools (including those from included child skills) become available to the actor's LLM agent for tool-calling.
As tool nodes in an Actor graph: An actor's graph definition can include type: tool nodes that directly invoke a specific tool. This is used for deterministic, non-LLM steps in a workflow — e.g., spawning a child plan, running validation, or executing a migration. The tool node either references a named registered tool or defines an anonymous inline tool.

block-beta
    columns 3
    space:3
    block:header:3
        A["Tool: Dual Role"]
    end
    space:3
    block:role1:1
        B["Role 1: In a Skill"]
        C["Skill: local/devops"]
        D["tools:"]
        E["  - local/run-migrations"]
        F["  - local/validate-schema"]
        G["(tool-calling by LLM)"]
    end
    space:1
    block:role2:1
        H["Role 2: In an Actor Graph"]
        I["Actor Graph node:"]
        J["  name: run_db"]
        K["  type: tool"]
        L["  tool: local/run-migrations"]
        M["(deterministic invoke)"]
    end

Tool Configuration (YAML)

Tools are defined in their own YAML configuration files, separate from skills and actors. A tool YAML file declares the tool's identity, schema, capability metadata, and implementation:

# File: tools/run-migrations.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/run-migrations
  description: "Run database migrations for the API service"

  source: custom     # mcp | agent_skill | builtin | custom

  # Resource bindings — what resources this tool needs access to
  resources:
    db:
      type: local/database
      access: read_write
      required: true
      description: "Target database for migrations"

  input_schema:
    type: object
    properties:
      direction:
        type: string
        enum: [up, down]
      count:
        type: integer
        default: 1
    required: [direction]

  capability:
    writes: true
    write_scope:
      resource_slots: [db]           # References the "db" resource slot
    checkpointable: true
    checkpoint_scope: transaction
    side_effects: [schema_mutation]

  code: |
    import subprocess
    direction = params["direction"]
    count = params.get("count", 1)
    db = ctx.resources["db"]          # Access the bound database resource
    result = subprocess.run(
        ["alembic", direction, str(count)],
        capture_output=True, text=True, cwd=db.sandbox.root
    )
    return {"stdout": result.stdout, "returncode": result.returncode}

Another example — a tool that wraps an MCP server endpoint:

# File: tools/create-github-issue.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/create-github-issue
  description: "Create a GitHub issue via MCP"

  source: mcp
  mcp_server:
    command: "npx @anthropic/mcp-github"
    env:
      GITHUB_TOKEN: "${GITHUB_TOKEN}"
    tool_name: create_issue   # The tool name as exposed by the MCP server

  capability:
    writes: true
    write_scope: [github:issues]
    checkpointable: false

And an Agent Skill tool:

# File: tools/deploy-staging.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/deploy-staging
  description: "Deploy the current branch to the staging environment"

  source: agent_skill
  agent_skill:
    path: ./skills/deploy-to-staging
    sandbox_policy: container
    allowed_tools: ["Bash(docker:*)", "Bash(kubectl:*)", "Read"]

  capability:
    writes: true
    checkpointable: false
    side_effects: [deploy, infrastructure]

Tool Registration and Management

Tools are managed through the agents tool CLI commands:

# Register a new tool from its YAML configuration
agents tool add local/run-migrations --config ./tools/run-migrations.yaml

# Upgrade an existing tool (re-reads the config file, overwrites registration)
agents tool add local/run-migrations --config ./tools/run-migrations.yaml --upgrade

# List all registered tools
agents tool list

# Show details for a tool (schema, capability, references)
agents tool show local/run-migrations

# Remove a tool
agents tool remove local/run-migrations

Once registered, a tool is available to be referenced by skills (in their tools list) and by actor graphs (as type: tool nodes). Tools persist in the database (local or server) and follow the same namespace rules as actors and skills.

Anonymous Tools

An anonymous tool is an inline tool definition that appears directly in a skill YAML or an actor graph node. Anonymous tools use the same format as a named tool's YAML definition (same input_schema, capability, and code fields) but lack a namespaced name. They are:

Not registered in the Tool Registry
Not reusable — they exist only within the YAML file where they are defined
Useful for one-off operations that are too specific to warrant separate registration

Anonymous tools in a skill YAML:

skill:
  name: local/my-skill
  tools:
    - local/run-migrations          # Named tool reference
    - local/validate-api-compat     # Named tool reference

  anonymous_tools:                  # Inline definitions, same format as tool YAML
    - description: "One-off data cleanup for this project"
      input_schema:
        type: object
        properties:
          table: { type: string }
      capability:
        writes: true
        checkpointable: true
      code: |
        # ... Python code ...
        return {"cleaned": count}

Anonymous tools in an actor graph node:

nodes:
  - name: custom_step
    type: tool
    anonymous: true
    description: "Inline validation specific to this workflow"
    input_schema:
      type: object
      properties:
        data: { type: object }
    capability:
      read_only: true
    code: |
      # ... Python code ...
      return {"valid": True}

The anonymous tool format is intentionally identical to the body of a named tool YAML — this means promoting an anonymous tool to a named, registered tool is a simple copy-paste into its own YAML file and agents tool add.

Metadata Overrides

When referencing a named tool in a skill or actor graph, its registered metadata can optionally be overridden at the point of use. This allows context-specific adjustments without modifying the tool's global registration.

Overriding tool metadata in a skill:

skill:
  name: local/strict-devops
  tools:
    - name: local/run-migrations
      override:
        capability:
          human_approval_required: true    # Override: require approval in this skill
          write_scope: [database:staging]  # Override: restrict scope for this context

    - local/validate-api-compat            # No overrides, use as registered

Overriding tool metadata in an actor graph node:

nodes:
  - name: safe_migrate
    type: tool
    tool: local/run-migrations
    override:
      capability:
        human_approval_required: true

Overriding tool metadata when including a sub-skill:

When a skill includes another skill (importing all its tools), individual tools from the included skill can have their metadata overridden:

skill:
  name: local/production-ops
  includes:
    - name: local/devops-toolkit
      tool_overrides:
        - tool: local/run-migrations
          override:
            capability:
              human_approval_required: true   # In this context, require human approval
              write_scope: [database:production]

        - tool: local/create-github-issue
          override:
            capability:
              required_permissions: [org:write]  # Stricter permissions in this context

Override rules:

Overrides are shallow-merged — only the specified fields are replaced; unspecified fields retain their registered values.
Overrides never persist back to the Tool Registry — they apply only at the point of use.
Built-in tool metadata cannot be overridden (it is authoritative from the implementation).
The override scope is limited to capability and description fields. Schema (input_schema, output_schema) cannot be overridden because it would break callers' expectations.

Resource Bindings

Tools operate on resources — git repositories, filesystems, databases, and more. The resource binding system declares and resolves the relationship between a tool and the resources it needs access to.

Resource Slots

A tool declares one or more resource slots in its YAML configuration. Each slot is a typed placeholder that specifies:

Slot name: A logical name used to reference the resource within the tool's code and parameters.
Resource type: The resource type required (e.g., git, fs-mount, local/database). The bound resource must be of this type (or a compatible subtype).
Access mode: read_only, write_only, or read_write.
Description: Human-readable explanation of what the tool uses this resource for.
Required/optional: Whether the slot must be bound for the tool to function.

Example tool YAML with resource slots:

tool:
  name: local/run-migrations
  description: "Run database migrations"
  source: custom

  resources:
    db:
      type: local/database
      access: read_write
      required: true
      description: "Target database for migrations"

  capability:
    writes: true
    write_scope: [db:migrations]     # References the "db" slot
    checkpointable: true

  code: |
    direction = params["direction"]
    db_resource = ctx.resources["db"]   # Access the bound resource
    result = db_resource.handler.execute_migration(direction, db_resource.sandbox)
    return {"status": "ok"}

A tool that works with multiple resources:

tool:
  name: local/cross-repo-diff
  description: "Compare files across two git repositories"
  source: custom

  resources:
    source_repo:
      type: git-checkout
      access: read_only
      required: true
      description: "Source repository to compare from"
    target_repo:
      type: git-checkout
      access: read_only
      required: true
      description: "Target repository to compare against"

  capability:
    read_only: true

  code: |
    source = ctx.resources["source_repo"]
    target = ctx.resources["target_repo"]
    # ... compare files across repos ...

Three Binding Modes

Resource slots are resolved to actual resources through one of three binding modes:

1. Contextual Binding (default)

The slot declares a resource type requirement, and the system resolves it from the plan's project context at activation time. This is the most common mode — the tool says "I need a git-checkout resource" and the system finds one among the project's linked resources.

resources:
  repo:
    type: git-checkout
    access: read_write
    # No `bind` field → contextual binding

Resolution rules for contextual binding:

The system searches the plan's project for linked resources matching the slot's type.
If exactly one resource of the right type exists, it is automatically bound.
If multiple resources match, the system uses the slot name as a hint (e.g., a slot named repo prefers a resource with alias repo). If ambiguous, the plan execution raises an error requiring explicit binding.
If no resource matches, the tool cannot be activated for this plan (a validation error is raised during plan creation).

2. Static Binding

The slot is hardcoded to a specific registered resource by name. This is useful for tools that always operate on the same resource, regardless of project context.

resources:
  docs:
    type: fs-mount
    access: read_only
    bind: local/company-docs     # Static: always this resource
    description: "Company documentation corpus"

Static bindings are resolved at registration time and validated — the named resource must exist and be of the correct type.

3. Parameter Binding

The resource reference is passed as a tool argument at invocation time. This is useful for tools that operate on user-specified resources.

resources:
  target:
    type: git-checkout
    access: read_only
    from_param: repository       # Bound from the "repository" input parameter
    description: "Repository to analyze"

input_schema:
  type: object
  properties:
    repository:
      type: string
      description: "Name of the registered resource to analyze"
  required: [repository]

The from_param field links a resource slot to an input parameter. At invocation time, the system resolves the parameter value as a resource name from the Resource Registry and validates type compatibility.

Binding Resolution Flow

stateDiagram-v2
    [*] --> ToolActivation: Actor references skill or tool node

    state "For Each Resource Slot" as ForEach {
        state binding_check <<choice>>
        [*] --> binding_check: Check binding type

        binding_check --> StaticBinding: has bind field
        binding_check --> ContextualBinding: no bind, no from_param
        binding_check --> ParameterBinding: has from_param

        state "Static Binding" as StaticBinding {
            [*] --> ResolveByName: Resolve from Resource Registry
            ResolveByName --> ValidateType: Validate type compatibility
        }

        state "Contextual Binding" as ContextualBinding {
            [*] --> SearchProject: Search plan's project resources
            SearchProject --> FilterByType: Filter by resource type
            state match_check <<choice>>
            FilterByType --> match_check
            match_check --> AutoBind: One match
            match_check --> TryAlias: Multiple matches
            match_check --> ValidationError: No matches
            TryAlias --> AliasMatch: Try alias/name match
            AliasMatch --> AutoBind: Match found
            AliasMatch --> ValidationError: No match
        }

        state "Parameter Binding" as ParameterBinding {
            [*] --> DeferBinding: Defer to invocation time
        }

        StaticBinding --> StoreBindings
        AutoBind --> StoreBindings
        ParameterBinding --> StoreBindings
        state "Store in ToolActivationContext" as StoreBindings
    }

    state "Tool Invocation" as Invocation {
        [*] --> ResolveParams: Resolve parameter-bound slots\nfrom invocation params
        [*] --> ValidateAccess: Ensure sandbox exists\nValidate access mode
        ResolveParams --> Execute
        ValidateAccess --> Execute
        state "Execute tool with bound resources" as Execute
    }

    ForEach --> Invocation
    Invocation --> [*]

Built-in Tool Resource Bindings

Built-in tools have implicit resource slots that do not need to be declared in YAML (they are hardcoded in the implementation):

Built-in Tool Group	Implicit Slot	Slot Type	Access
`file_operations` (read_file, write_file, edit_file, etc.)	`directory`	`fs-directory` or `git-checkout`	`read_write`
`directory_operations` (create_directory, list_directory, etc.)	`directory`	`fs-directory` or `git-checkout`	`read_write`
`search_operations` (search_files, find_definition, etc.)	`directory`	`fs-directory` or `git-checkout`	`read_only`
`git_operations` (git_status, git_diff, git_log, etc.)	`repo`	`git-checkout`	`read_only`

Built-in tools accept both fs-directory and git-checkout types for file operations because a git-checkout resource's worktree root is an fs-directory. When binding to a git-checkout, the resource router automatically resolves to the worktree root fs-directory child for file operations. A standalone fs-mount resource also works — the router resolves through the fs-mount → root fs-directory chain.

Resource Discovery via Bindings

The binding system enables powerful resource discovery queries:

"What tools can modify this resource?" → Find all tools with resource slots matching the resource's type and access: read_write or access: write_only.
"What tools can read this virtual file?" → Find the virtual file's physical children, then find tools with slots matching each physical resource's type.
"What resources does this tool need?" → Inspect the tool's declared resource slots.
"Is this tool compatible with this project?" → Check if the project's linked resources can satisfy all of the tool's required resource slots.

Tool Registry

CleverAgents maintains a Tool Registry — a persistent catalog of all independently registered tools:

@startuml
skinparam classAttributeIconSize 0
skinparam classFontSize 13
skinparam noteFontSize 11
skinparam defaultFontSize 12

class ToolRegistry {
  - toolIndex : Map<String, ToolRecord>
  --
  + add(config_path) : ToolRecord
  + upgrade(name, config_path) : ToolRecord
  + remove(name) : void
  + lookup(name) : ToolRecord
  + list(filters) : ToolRecord[]
}

class ToolRecord {
  + name : String
  + description : String
  + source : String {mcp|agent_skill|builtin|custom}
  + config_path : String
  + input_schema : JSONSchema
  + output_schema : JSONSchema
  + capability_metadata : CapabilityMetadata
  + resource_slots : List<ResourceSlot>
  + code : String
}

ToolRegistry "1" *-- "0..*" ToolRecord : indexes >

note right of ToolRegistry
  **Populated by:**
  - agents tool add CLI command
  - Dynamic refresh on MCP notifications

  **Consumed by:**
  - Skill registration
  - Actor graph construction
  - Resource binding resolution
  - Plan validation
  - Permission enforcement
end note
@enduml

The Tool Registry works alongside the Skill Registry (described in the Skills section). Skills reference tools by name from the Tool Registry; the Skill Registry's flattened tool sets are composed from Tool Registry entries plus any anonymous inline tools.

Tool Interface and Architecture

Each individual tool — whether independently registered or defined as an anonymous inline tool — conforms to a uniform interface regardless of its source:

@startuml
skinparam classAttributeIconSize 0
skinparam classFontSize 13
skinparam defaultFontSize 12
skinparam linetype ortho

class Tool {
}

class Identity {
  + name : String
  + qualified_name : String
  + source : ToolSource
}

class Schema {
  + input_schema : JSONSchema
  + output_schema : JSONSchema
}

class CapabilityMetadata {
  + read_only : Boolean
  + writes : Boolean
  + write_scope : String
  + idempotent : Boolean
  + checkpointable : Boolean
  + side_effects : List<String>
  + required_permissions : List<String>
  + cost_profile : String
  + human_approval_required : Boolean
}

class ResourceBindings {
  + slots : Map<String, ResourceSlot>
}

class ResourceSlot {
  + type : String
  + access : String
  + required : Boolean
  + bind : String
  + from_param : String
  + description : String
}

interface Lifecycle <<interface>> {
  + discover() : ToolDescriptor
  + activate() : void
  + execute(params, ctx) : Result
  + deactivate() : void
}

class ExecutionContext {
  + sandbox : Sandbox
  + plan : Plan
  + changes : List<Change>
  + resources : Map<String, BoundResource>
}

enum ToolSource {
  mcp
  agent_skill
  builtin
  custom
}

Tool *-- Identity
Tool *-- Schema
Tool *-- CapabilityMetadata
Tool *-- ResourceBindings
Tool *-- Lifecycle
Tool o-- ExecutionContext : uses at runtime >
ResourceBindings *-- "0..*" ResourceSlot
Identity --> ToolSource
@enduml

Every tool implements the same four lifecycle methods. The tool adapter layer is responsible for translating source-specific behavior into these methods.

Tool Adapter Layer

Each tool source has a corresponding adapter that translates source-specific protocols into the uniform tool interface:

@startuml
skinparam classAttributeIconSize 0
skinparam classFontSize 13
skinparam defaultFontSize 12

interface "ToolInterface" as UTI <<interface>> {
  + discover() : ToolDescriptor
  + activate() : void
  + execute(params, ctx) : Result
  + deactivate() : void
}

class MCPToolAdapter {
  + discover() : ToolDescriptor
  .. tools/list RPC → descriptors ..
  + activate() : void
  .. spawn server, init JSON-RPC ..
  + execute(params, ctx) : Result
  .. tools/call RPC → result ..
  + deactivate() : void
  .. shutdown server ..
}

class AgentSkillAdapter {
  + discover() : ToolDescriptor
  .. parse SKILL.md frontmatter ..
  + activate() : void
  .. load SKILL.md body into agent context ..
  + execute(params, ctx) : Result
  .. agent follows instructions, runs scripts ..
  + deactivate() : void
  .. remove from context ..
}

class BuiltinAdapter {
  + discover() : ToolDescriptor
  .. return hardcoded descriptors ..
  + activate() : void
  .. no-op ..
  + execute(params, ctx) : Result
  .. call native Python impl ..
  + deactivate() : void
  .. no-op ..
}

MCPToolAdapter .up.|> UTI
AgentSkillAdapter .up.|> UTI
BuiltinAdapter .up.|> UTI
@enduml

MCPToolAdapter

Bridges external MCP servers into the tool model:

discover(): Spawns the MCP server process (or connects to a remote Streamable HTTP endpoint), performs the MCP initialize handshake, negotiates capabilities, then calls tools/list to enumerate available tools. Each MCP tool becomes a separate ToolDescriptor with its inputSchema and inferred capability metadata.
activate(): Ensures the MCP server process is running and the JSON-RPC connection is healthy. For remote servers, validates the authentication token. Registers for notifications/tools/list_changed so CleverAgents can dynamically update available tools.
execute(): Translates a Tool.execute(params, ctx) call into an MCP tools/call JSON-RPC request. Before dispatching:
- Rewrites file paths to sandbox-relative paths
- Validates params against inputSchema
- Checks capability metadata against plan permissions
- Creates a checkpoint if the tool is marked checkpointable
After the MCP tool returns its content[] response, the adapter:
- Parses the result into the CleverAgents Result format
- Records any resource mutations as Change objects in the plan's ChangeSet
deactivate(): Sends a clean shutdown to the MCP server process and closes the JSON-RPC connection.

Capability inference: MCP tools expose limited metadata (name, description, inputSchema). The adapter infers extended capability metadata using heuristics:

Tools whose names contain read, get, list, search, find → read_only: true
Tools whose names contain write, create, update, delete, set → writes: true
All inferences can be overridden via the overrides block in tool or skill YAML

AgentSkillAdapter

Bridges Agent Skills Standard (SKILL.md folders) into the tool model. Agent Skills are fundamentally different from MCP tools — they are instruction-driven rather than schema-driven. An Agent Skill is not a single function call; it is a bundle of procedural knowledge that an LLM agent loads into its context and follows.

discover(): Scans the configured skill directory for a SKILL.md file. Parses only the YAML frontmatter (name, description, optional compatibility, metadata, allowed-tools) to produce a lightweight ToolDescriptor. This metadata is injected into the agent's system prompt in a structured format so the LLM can decide when the skill is relevant:
```
<available_agent_skills>
  <agent_skill>
    <name>deploy-to-staging</name>
    <description>Deploy the current branch to the staging environment.</description>
    <tool>local/deploy-staging</tool>
  </agent_skill>
</available_agent_skills>
```
Discovery is low-cost — only ~50–100 tokens per Agent Skill for metadata. The full instructions are not loaded until activation.
activate(): When the LLM agent determines (or is instructed) that a task matches the skill's description, the adapter loads the full SKILL.md Markdown body into the agent's active context. This injects step-by-step instructions, examples, edge cases, and references to bundled scripts. The tool is now "active" — the agent has the procedural knowledge to execute it.

If the skill references additional files (references/*.md, scripts/*.py, assets/*), these are made available on demand — the agent can read them as needed, following the Agent Skills Standard's progressive disclosure model.
execute(): Unlike MCP tools (which are single RPC calls), Agent Skill execution is agent-mediated. The LLM agent follows the loaded instructions, potentially:
- Running bundled scripts via shell execution (sandboxed)
- Reading reference files for additional context
- Using other available tools (e.g., built-in file operations) as part of the procedure
- Making multiple tool calls in sequence to accomplish the workflow
The adapter wraps this execution in a tool execution context so that all mutations are tracked, sandboxed, and checkpointable. Script execution respects the allowed_tools and sandbox_policy declared in the tool's YAML.
deactivate(): Removes the skill's instructions from the agent's active context to free up token budget. The skill's metadata remains available for re-activation.

Key design principle: Agent Skills extend the agent's knowledge, not just its toolset. An Agent Skill can teach an agent a multi-step workflow that involves calling multiple other tools, making decisions based on intermediate results, and following domain-specific best practices — something a single MCP tool call cannot express.

BuiltinToolAdapter

Wraps CleverAgents' native resource operations as tools:

discover(): Returns hardcoded ToolDescriptor objects for each built-in operation. These descriptors have fully specified capability metadata since the implementation is first-party.
activate(): No-op. Built-in tools are always available.
execute(): Calls the native Python implementation directly. Built-in tools operate through the resource abstraction layer, automatically integrating with sandbox path mapping, change tracking, and checkpointing.
deactivate(): No-op.

Built-in tool groups:

File Operations (file_operations):

read_file(path: str) -> str
write_file(path: str, content: str) -> None
edit_file(path: str, edits: list[Edit]) -> None
delete_file(path: str) -> None
move_file(source: str, destination: str) -> None
copy_file(source: str, destination: str) -> None

Directory Operations (directory_operations):

create_directory(path: str) -> None
list_directory(path: str, pattern: str = "*") -> list[str]
delete_directory(path: str, recursive: bool = False) -> None

Search Operations (search_operations):

search_files(pattern: str, content_pattern: str = None) -> list[Match]
find_definition(symbol: str) -> list[Location]
find_references(symbol: str) -> list[Location]

Git Operations (git_operations, when resource is a git repository):

git_status() -> GitStatus
git_diff(path: str = None) -> str
git_log(count: int = 10) -> list[Commit]
git_blame(path: str) -> list[BlameLine]

Each built-in tool:

Has fully defined capability metadata
Operates through the resource abstraction layer
Automatically tracks changes to the ChangeSet
Respects sandbox boundaries and deny-lists

Tool Capability Metadata (Critical for Safety)

MCP's metadata is not sufficient (read-only/idempotent is not enough; write scope is unclear). CleverAgents extends every tool — regardless of source — with a uniform capability metadata schema:

capability:
  read_only: bool          # Whether tool only performs read operations
  writes: bool             # Whether tool can modify resources
  write_scope:             # What the tool is allowed to mutate
    - file_paths: ["src/**", "tests/**"]     # Path patterns within bound resources
    - resource_slots: ["repo", "db"]         # Resource slot names (from resource bindings)
    - environment: container | host
  idempotent: bool         # Whether repeated calls produce same result
  checkpointable: bool     # Whether tool supports checkpoint/rollback
  checkpoint_scope: str    # What can be rolled back (file, transaction, commit, snapshot)
  side_effects:            # Non-reversible effects
    - install_packages
    - mutate_infra
    - send_email
  required_permissions:    # Permissions needed to invoke
    - resource:write
    - sandbox:shell
  cost_profile:            # Usage constraints
    rate_limit: "10/min"
    estimated_cost: "$0.01/call"
  human_approval_required: bool  # Whether a human must approve invocation

Where metadata comes from per source:

Source	Metadata origin	Override mechanism
Built-in	Hardcoded in implementation	Not overridable (authoritative)
MCP	Inferred from tool name/description + MCP annotations	`overrides` block in tool or skill YAML; `override` at skill/actor reference point
Agent Skill	Declared in SKILL.md frontmatter `metadata` + inferred from `allowed-tools`	Tool YAML `capability` block; `override` at skill/actor reference point
Custom	Manually declared in tool YAML `capability` block	`override` at skill/actor reference point (author is the source of truth for registered values)

Read-Only Actions and Tool Permissions

When an action is marked read_only: true, it can only use tools that have read_only: true in their capability metadata. This is enforced at runtime by the tool execution context — any attempt to invoke a tool with writes: true from a read-only plan raises a PermissionDeniedError.

Tool Execution Flow

When an LLM agent decides to use a tool (regardless of source), the following flow occurs through the unified execution pipeline:

1. LLM generates tool call
   e.g., edit_file(path="src/main.py", changes=[...])
   or:   local/github.create_issue(title="Bug fix", body="...")
   or:   (activates Agent Skill "deploy-to-staging" via instructions)
                                ↓
2. Tool Router receives call
   - Resolves tool by name from the Tool Registry or actor's skill tool sets
   - Validates parameters against inputSchema
   - Checks capability metadata against plan's permission policy:
     • Is this tool in allowed skill categories?
     • Does the plan allow writes?
     • Is human approval required?
   - If denied → return PermissionDeniedError to LLM
                                ↓
3. Resource Binding Resolution & Sandbox Context
   - Resolve resource bindings for this tool:
     • Static bindings: already resolved at registration
     • Contextual bindings: resolve from plan's project resources
     • Parameter bindings: resolve from invocation arguments
   - Validate resource type compatibility for each slot
   - Validate access mode (e.g., read_write tool on read_only resource → error)
   - Ensure sandbox exists for each bound resource (lazy sandboxing)
   - Maps logical paths to sandbox-relative paths via bound resource handlers
   - Inject bound resources into ctx.resources[slot_name]
   - If tool is checkpointable → create pre-execution checkpoint
                                ↓
4. Adapter-Specific Execution
   - MCP: sends tools/call JSON-RPC to server process
   - Agent Skill: agent follows loaded SKILL.md instructions,
     running scripts and tools in sandboxed shell
   - Built-in: calls native Python implementation directly
   - Custom: executes inline code with sandboxed context
                                ↓
5. Change Recording
   - If tool modified resources → create Change record(s)
   - Append Change(s) to plan's ChangeSet
   - Update sandbox state
   - If checkpointable → record checkpoint for rollback
                                ↓
6. Result Return
   - Normalize result to uniform Result type
   - Return to LLM agent for continued reasoning

Change Tracking from Tool Invocations

Critical Architecture Point: The ChangeSet is NOT built by parsing LLM output. It is built by recording the effects of tool invocations:

class ToolExecutionContext:
    """Context provided to every tool execution, regardless of source."""
    
    def __init__(self, plan: Plan, sandbox: Sandbox,
                 resources: dict[str, BoundResource]):
        self.plan = plan
        self.sandbox = sandbox
        self.resources = resources    # slot_name → BoundResource
        self.changes: list[Change] = []
    
    def record_change(self, change: Change) -> None:
        """Record a change made by a tool."""
        self.changes.append(change)
        self.plan.changeset.add_change(change)


class WriteFileTool:
    """Example: built-in tool for writing files."""
    
    def execute(self, path: str, content: str, ctx: ToolExecutionContext) -> None:
        handler = ctx.sandbox.get_handler(path)
        change = handler.write(path, content, ctx.sandbox)
        ctx.record_change(change)

This approach means:

Every resource modification is explicit and tracked
The ChangeSet accurately reflects what was done, not what was said
Rollback is precise (replay inverse of recorded changes)
Audit logs show exactly which tool invocation produced each change

MCP Integration Details

MCP Concepts Mapping

MCP Concept	CleverAgents Equivalent	Extension
Tool	Independently registered Tool (source: mcp), referenced by skills	Extended capability metadata (write_scope, checkpointable, side_effects)
Resource	Resource	Extended to support both read AND write operations
Prompt	Action template	Full plan lifecycle (Strategize → Execute → Apply)
Server	MCP Server connection (declared in tool or skill YAML)	Managed by MCPToolAdapter with lifecycle and reconnection
JSON-RPC	Internal adapter protocol	Abstracted behind Tool.execute()

MCP Server Lifecycle Management

CleverAgents manages MCP server processes as part of the tool/skill/actor lifecycle:

sequenceDiagram
    participant CLI as CLI
    participant Reg as Registry
    participant ActorRT as Actor Runtime
    participant Adapter as MCPToolAdapter
    participant MCP as MCP Server

    note over CLI,Reg: Phase 1 - Registration
    CLI->>Reg: agents tool add or skill add
    Reg->>Reg: Validate server command or endpoint
    Reg->>Reg: Store server config in record

    note over ActorRT,MCP: Phase 2 - Actor Activation
    ActorRT->>Adapter: Activate (for each MCP server)
    Adapter->>MCP: Spawn process (stdio) or connect (HTTP)
    Adapter->>MCP: MCP initialize handshake
    MCP-->>Adapter: Capabilities
    Adapter->>MCP: tools list
    MCP-->>Adapter: Tool descriptors
    Adapter->>MCP: Subscribe notifications tools list_changed

    note over ActorRT,MCP: Phase 3 - Execution
    ActorRT->>Adapter: LLM generates tool call
    Adapter->>MCP: tools call (JSON-RPC)
    MCP-->>Adapter: Result
    Adapter->>ActorRT: Result + Change tracking

    note over ActorRT,MCP: Phase 4 - Deactivation
    ActorRT->>Adapter: Deactivate
    Adapter->>MCP: Clean shutdown

Sandbox Path Rewriting for MCP Tools

MCP servers operate on real filesystem paths, but CleverAgents executes plans in sandboxes. The MCPToolAdapter transparently rewrites paths:

# Before sending to MCP server:
# Logical path: "src/main.py"
# Sandbox path: "/tmp/sandbox-01HXM/worktree/src/main.py"
# The adapter rewrites the tool arguments so the MCP server
# operates on sandboxed state without knowing about the sandbox.

This ensures MCP tools respect sandbox boundaries even though they have no awareness of the CleverAgents sandbox model.

Agent Skills Integration Details

Discovery and Progressive Disclosure

Agent Skills follow a three-tier progressive disclosure model that maps directly to the tool lifecycle:

Tier	What loads	When	Token cost
Metadata	`name` + `description` from SKILL.md frontmatter	Tool registration / actor activation	~50–100 tokens per Agent Skill
Instructions	Full SKILL.md Markdown body	When LLM determines task matches the skill (activate phase)	Recommended < 5000 tokens
Resources	`scripts/`, `references/`, `assets/`	On demand during execution	Variable

This means an actor can have dozens of Agent Skill tools available but only pay the token cost for their metadata at startup. Full instructions load only when relevant.

Agent Skills vs. MCP Tools: When to Use Which

Dimension	MCP Tools	Agent Skills
Interaction model	Single function call with JSON params/result	Multi-step procedure with instructions the agent follows
Knowledge type	"Here is a function you can call"	"Here is how to accomplish a complex task"
Statefulness	Stateless per-call	Stateful across multiple tool calls within a procedure
Authoring	Implement an MCP server (code)	Write a SKILL.md file (prose + optional scripts)
Portability	Any MCP-compatible host	Any Agent Skills-compatible agent
Best for	Atomic operations (CRUD, queries, API calls)	Complex workflows (code review processes, deployment procedures, data analysis pipelines)

Both can coexist in the same skill. A common pattern is an Agent Skill tool that teaches the agent a workflow which involves calling multiple MCP tools:

Agent Skill Tool: "local/deploy-staging"
  SKILL.md instructions:
    1. Run tests using the built-in shell tool
    2. Create a PR using the GitHub MCP tool (create_pull_request)
    3. Wait for CI using the GitHub MCP tool (get_check_runs)
    4. Deploy using the AWS MCP tool (ecs_update_service)
    5. Verify deployment using the HTTP MCP tool (fetch_url)

Tool-Level Checkpointability

Each tool declares whether it supports checkpoint/rollback via its capability metadata. Checkpointing behavior varies by source:

Source	Checkpoint mechanism
Built-in file ops	Snapshot file state pre-modification; rollback restores file content
Built-in git ops	Create commit or stash; rollback via `git reset` / `git checkout`
MCP tools	Adapter-created checkpoints of affected resources; rollback replays inverse operations where possible
Agent Skills	Composite — each sub-tool-call within the skill's execution is individually checkpointed
Custom (containerized)	Filesystem snapshot or container image layer; rollback restores snapshot

Checkpointing is easier when tool scope is constrained (e.g., "only files within a sandbox worktree + git"). The capability metadata's checkpoint_scope field communicates what granularity of rollback is supported.

When require_checkpoints is enabled on a plan, the plan may only use tools that have checkpointable: true. If disabled, the plan may use more generic/unsafe tools with fewer restrictions (useful for low-stakes tasks).

Skills

What a Skill Is

A skill is a namespaced, reusable collection of tools that is registered in the system via its own YAML configuration file and managed through agents skill CLI commands. Skills are the unit of capability composition in CleverAgents — they define what an actor can do by assembling tools into coherent, reusable bundles.

A skill is not a single tool. It is a container that references one or more tools (by name from the Tool Registry) and/or defines anonymous inline tools, along with metadata describing the collection's purpose, capabilities, and safety characteristics. Tools are independently registered, callable operations (see the Tools section above). Skills organize them into reusable groups.

Key properties of a skill:

Named and namespaced: Skills follow the same <namespace>/<name> naming convention as actors, tools, actions, and plans (e.g., local/github-ops, cleverthis/file-management, local/deploy-tools).
Defined in their own YAML files: Skills are NOT defined inline in actor configurations. They have their own configuration files and are managed as independent, reusable entities.
A collection of tools: Each skill references named tools from the Tool Registry and/or defines anonymous inline tools. Skills can also expose tools from MCP servers, Agent Skills Standard folders, and built-in tool groups.
Hierarchically composable: A skill can include other skills by reference, inheriting all of their tools. This enables layered composition — a "full-stack" skill might include a "file-ops" skill, a "git-ops" skill, and a "github" skill. When including a sub-skill, individual tool metadata can optionally be overridden.
Referenced by actors: Actors reference skills by fully-qualified name. The actor's graph gains access to all tools within the referenced skills.

The Skill / Tool Distinction

@startuml
skinparam packageStyle rectangle
skinparam defaultFontSize 12
skinparam componentFontSize 12

package "Skill: local/devops-toolkit" as Skill {
  package "builtin: file_operations" as FileOps {
    component [read_file()] as T1
    component [write_file()] as T2
    component [edit_file()] as T3
  }

  package "builtin: git_operations" as GitOps {
    component [git_status()] as T4
    component [git_diff()] as T5
  }

  package "mcp: github-server" as GH {
    component [create_issue()] as T6
    component [create_pr()] as T7
    component [list_repos()] as T8
  }

  package "custom" as Custom {
    component [run_migrations()] as T9
  }

  package "Included Skills" as Includes {
    component [local/pdf-processing\n(adds pdf tools)] as I1
    component [local/data-analysis\n(adds analysis tools)] as I2
  }
}
@enduml

Tools are independently registered, atomic units of execution (see the Tools section above for full details). Each tool has:

A namespaced name, description, and JSON Schema for inputs/outputs
Its own YAML configuration file, registered via agents tool add
A source type (mcp, agent_skill, builtin, custom)
Capability metadata (read_only, writes, checkpointable, etc.)
A lifecycle: discover(), activate(), execute(params, ctx), deactivate()

Skills are the organizational units. Each skill has:

A namespaced name
A YAML configuration file defining its tool composition
Zero or more named tool references (pointing to independently registered tools in the Tool Registry)
Zero or more anonymous inline tools (one-off tools defined directly in the skill YAML)
Zero or more included child skills (whose tools are merged in, with optional per-tool metadata overrides)
Tool sources: MCP servers, Agent Skills folders, built-in tool groups
Metadata (description, capability summary)

When an actor references a skill, it gains access to the flattened set of all tools — named tool references, anonymous tools, tools from MCP/Agent Skills/builtins, and those inherited from included child skills.

Skill Configuration (YAML)

Skills are defined in their own YAML configuration files, separate from tool and actor configurations. A skill YAML file declares which registered tools it includes (by name), which other skills it includes, and optionally defines anonymous inline tools:

# File: skills/devops-toolkit.yaml
cleveragents:
  version: "3.0"

skill:
  name: local/devops-toolkit
  description: "Full-stack development tools for file ops, git, GitHub, and deployment"

  # ── Named Tool References ───────────────────────────────
  # Reference independently registered tools by name.
  # These tools must already be registered via `agents tool add`.
  # Optional metadata overrides can be applied per tool.
  tools:
    - local/run-migrations                  # Simple reference, use as registered
    - name: local/deploy-staging            # Reference with metadata override
      override:
        capability:
          human_approval_required: true     # Require approval in this skill context

  # ── Include other skills ─────────────────────────────────
  # All tools from included skills become part of this skill.
  # Included skills must already be registered in the system.
  # Individual tools from included skills can have metadata overridden.
  includes:
    - local/file-ops           # built-in file + directory + search tools
    - local/git-ops            # built-in git tools
    - name: local/github       # MCP-based GitHub tools, with per-tool overrides
      tool_overrides:
        - tool: local/create-github-issue
          override:
            capability:
              write_scope: [github:issues:org-only]

  # ── MCP Server Tools ─────────────────────────────────────
  # Connect to MCP servers and expose their tools.
  # Tools discovered from MCP servers are auto-registered in the
  # Tool Registry if not already present.
  mcp_servers:
    - name: linear
      command: "npx @anthropic/mcp-linear"
      env:
        LINEAR_API_KEY: "${LINEAR_API_KEY}"
      # Optional: override inferred capability metadata per tool
      overrides:
        - tool: create_issue
          writes: true
          write_scope: [linear:issues]
        - tool: list_issues
          read_only: true

  # ── Agent Skills (SKILL.md folders) ──────────────────────
  # Each Agent Skill folder is loaded as a composite tool.
  # The agent discovers it via metadata, activates it by
  # loading SKILL.md instructions, and follows them.
  agent_skills:
    - path: ./skills/code-review-checklist
      sandbox_policy: none

  # ── Built-in Tool Groups ─────────────────────────────────
  # Opt-in to built-in tool groups provided by CleverAgents.
  builtins:
    - group: shell_operations

  # ── Anonymous Tools ──────────────────────────────────────
  # Inline tool definitions for one-off, skill-specific operations.
  # Same format as a named tool YAML body but without a name.
  # These are NOT registered in the Tool Registry and are NOT reusable.
  anonymous_tools:
    - description: "One-off cleanup for legacy migration artifacts"
      input_schema:
        type: object
        properties:
          directory: { type: string }
      capability:
        writes: true
        checkpointable: true
        checkpoint_scope: file
      code: |
        import os, glob
        directory = params["directory"]
        removed = []
        for f in glob.glob(os.path.join(ctx.sandbox.root, directory, "*.legacy")):
            os.remove(f)
            removed.append(f)
        return {"removed": removed, "count": len(removed)}

Here is an example of a simpler skill that wraps only built-in tools, suitable for common reuse:

# File: skills/file-ops.yaml
cleveragents:
  version: "3.0"

skill:
  name: local/file-ops
  description: "File, directory, and search operations"

  builtins:
    - group: file_operations      # read, write, edit, delete, move, copy
    - group: directory_operations  # create, list, delete dirs
    - group: search_operations     # search files, find definitions/references

And an example of a skill that is purely MCP-based:

# File: skills/github.yaml
cleveragents:
  version: "3.0"

skill:
  name: local/github
  description: "GitHub operations via MCP"

  mcp_servers:
    - name: github
      command: "npx @anthropic/mcp-github"
      env:
        GITHUB_TOKEN: "${GITHUB_TOKEN}"
      overrides:
        - tool: create_issue
          writes: true
          write_scope: [github:issues]
          checkpointable: false
        - tool: create_pull_request
          writes: true
          write_scope: [github:pulls]
          checkpointable: false
        - tool: list_repos
          read_only: true
        - tool: get_file_contents
          read_only: true

Skill Hierarchy and Composition

Skills can include other skills via the includes field. When a skill includes another, all tools from the child skill (and transitively, all tools from any skills it includes) become part of the parent skill's flattened tool set.

local/full-stack-dev
  ├── includes: local/file-ops
  │     └── builtins: file_operations, directory_operations, search_operations
  ├── includes: local/git-ops
  │     └── builtins: git_operations
  ├── includes: local/github
  │     └── mcp_servers: github (create_issue, create_pr, list_repos, ...)
  ├── agent_skills: code-review-checklist
  └── tools: local/run-migrations, local/deploy-staging  (named tool refs)

  Flattened tool set available to actors referencing local/full-stack-dev:
    read_file, write_file, edit_file, delete_file, move_file, copy_file,
    create_directory, list_directory, delete_directory,
    search_files, find_definition, find_references,
    git_status, git_diff, git_log, git_blame,
    create_issue, create_pr, list_repos, get_file_contents,
    code-review-checklist (agent skill),
    local/run-migrations, local/deploy-staging (named tools)

Rules for skill composition:

Circular includes are forbidden. The system validates the include graph at registration time and rejects cycles.
Tool name conflicts: If two included skills provide tools with the same name, the conflict is resolved by qualification — the tool must be referenced as <skill_name>.<tool_name> (e.g., local/github.create_issue vs local/linear.create_issue). Direct tools (defined in the skill itself) take precedence over included tools.
Included skills must be registered before the including skill can be added. The agents skill add command validates this.
Depth is unlimited but the flattened tool set is computed at registration time and cached. Deep hierarchies do not incur runtime overhead.

Skill Registration and Management

Skills are managed through the agents skill CLI commands. Named tools referenced by skills must first be registered via agents tool add (see the Tools section):

# First, register any named tools the skill will reference
agents tool add local/run-migrations --config ./tools/run-migrations.yaml
agents tool add local/deploy-staging --config ./tools/deploy-staging.yaml

# Then register the skill (which references those tools by name)
agents skill add local/devops-toolkit --config ./skills/devops-toolkit.yaml

# Upgrade an existing skill (re-reads the config file, overwrites registration)
agents skill add local/devops-toolkit --config ./skills/devops-toolkit.yaml --upgrade

# List all registered skills
agents skill list

# Show details for a skill (tools, includes, metadata)
agents skill show local/devops-toolkit

# List all tools provided by a skill (flattened, including from child skills)
agents skill tools local/devops-toolkit

# Remove a skill
agents skill remove local/devops-toolkit

Once registered, a skill is available to be referenced by any actor configuration. Skills persist in the database (local or server) and follow the same namespace rules as actors, tools, and actions.

Actor References to Skills and Tools

Actors reference skills by name to make collections of tools available for LLM tool-calling. Additionally, actor graphs can include tool nodes that directly reference named tools or define anonymous inline tools (see Nodes in the Graph in the Actor section).

The actor's configuration lists which skills it should have access to:

# File: actors/code-assistant.yaml
cleveragents:
  version: "3.0"
  default_actor: code_assistant

actors:
  code_assistant:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      temperature: 0.3
      system_prompt: |
        You are a code assistant with access to file, git, and GitHub tools.
        Current task: {{ context.task_description }}

    # Reference skills by fully-qualified name.
    # All tools from these skills become available to this actor.
    skills:
      - local/file-ops
      - local/git-ops
      - local/github

  # Or reference a single composite skill that includes all of the above
  full_stack_assistant:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      system_prompt: |
        You are a full-stack development assistant.

    skills:
      - local/full-stack-dev    # includes file-ops, git-ops, github, etc.

Server-qualified skill references: When connected to multiple servers, skills can be disambiguated with a server prefix, same as actors:

skills:
  - dev:freemo/custom-analysis     # from dev server, personal namespace
  - prod:cleverthis/deploy-tools   # from prod server, org namespace
  - local/file-ops                 # local skill

Skill Registry

To enable plan validation, permission enforcement, and discovery at scale, CleverAgents maintains two registries that work together:

Tool Registry — a persistent catalog of all independently registered tools (described in the Tools section above). Managed via agents tool add/remove/list/show.
Skill Registry — a persistent catalog of all registered skills and their flattened tool sets. The Skill Registry composes its tool sets by resolving named tool references from the Tool Registry, incorporating anonymous inline tools, and merging tools from included child skills.

@startuml
skinparam classAttributeIconSize 0
skinparam classFontSize 13
skinparam defaultFontSize 12

class SkillRegistry {
  - skillIndex : Map<String, SkillRecord>
  --
  + add(config_path) : SkillRecord
  + upgrade(name, config_path) : SkillRecord
  + remove(name) : void
  + lookup(name) : SkillRecord
  + list(filters) : SkillRecord[]
  + tools(name) : ToolDescriptor[]
  + validate_plan(plan) : ValidationResult
  + refresh(name) : void
}

class SkillRecord {
  + name : String
  + description : String
  + config_path : String
  + includes : List<String>
  + tool_refs : List<String>
  + anonymous_tools : List<ToolDef>
  + flattened_tools : List<ToolDescriptor>
  + overrides : Map<String, Object>
  + capability_summary : CapabilitySummary
}

SkillRegistry "1" *-- "0..*" SkillRecord : indexes >

note right of SkillRegistry
  **Populated by:**
  - agents skill add CLI command
  - Dynamic refresh on MCP notifications

  **Depends on:**
  - Tool Registry (resolve named tool references)

  **Consumed by:**
  - Actor activation
  - Plan validation
  - Permission enforcement
  - Agent context injection
end note
@enduml

Both registries persist in the database (local SQLite or server). MCP server tools are refreshed dynamically when notifications/tools/list_changed events are received.

Session

What a Session Is

A session is a user's interactive thread with CleverAgents across time.

A session should:

maintain conversational continuity,
store plan references,
persist memory (if enabled),
provide a UI anchor (CLI invocation, TUI workspace, web session).

Session and Memory Persistence

The notes include a known issue: conversation history can be lost between CLI invocations depending on connection string configuration, implying the system needs a stable memory service backend.

Therefore, CleverAgents should specify:

sessions have stable IDs
sessions can be resumed
session storage backend is configured explicitly
if session persistence is disabled, the UX should be explicit about it (no silent history loss)

Server

What a Server Is

A server is an optional mode that enables:

multi-user access
shared org namespaces (<username>/ and <orgname>/)
persistent plan records
remote plan execution
permissioning and governance

Single-user local mode is the default (so setup is easy), but the architecture anticipates server mode for shared skills and org-level actions.

Client-Only vs Server Mode

Mode	Description	Plan Execution
Client-only	No server connection. All data in local database.	Always local
Server mode	Connected to a CleverAgents server. Namespaced items sync.	Local or server

It is possible to run a client with no server at all. Server is optional.

Plan Execution Location

Where a plan executes depends on the project type:

Project Type	Client Execution	Server Execution
Local (has local-only resources)	✅ Yes	❌ No (server can't access local resources)
Remote (all resources remotely accessible)	✅ Yes	✅ Yes

When acting on local projects, the client must be running because only the client can access local resources.

Remote projects can execute on either:

The client (if user prefers local execution)
The server (for long-running plans, since client may be transient)

Server Execution Benefits

Server execution is useful when:

Plans take a long time to execute
Client may disconnect (laptop closes, network issues)
Multiple team members need to monitor plan progress
Centralized logging and auditing required

No Plan Queuing

Plans are not queued. When a plan is used on projects and executed, it runs immediately. There is no worker queue or delayed execution model.

Multi-user Risks and Prompt Injection

Prompt injection isn't critical in single-user mode but becomes important for multi-user server environments.

Server mode must include:

permission boundaries
prompt sanitization / safe templating
resource access controls
auditing

Permissions

Permissions exist at multiple layers:

1) Namespace-level permissions

Who can create/edit org entities (actions, actors, tools, skills, resources, projects)?
Who can run them?

2) Project-level permissions

Who can modify project resources?
Who can apply changes?

3) Plan-level permissions

Can this plan write?
Does it require approvals?
Can it access restricted skills?

4) Skill-level permissions

Some skills should require:
- explicit user approval per call, or
- elevated role membership.

5) Resource-level permissions

Who can register/modify/remove resources in a namespace?
Who can link a resource to a project?
Per-resource access control:
- Some resources may be restricted to specific roles (e.g., production databases)
- Read-only vs. read-write access can be enforced per resource per project (via project-level overrides)
- Sensitive resources can require explicit approval before sandbox creation or tool binding

Approval Gates by Phase (Recommended)

A simple and powerful governance model:

Strategize: generally safe, read-only → minimal restrictions
Execute: writes occur but sandboxed → moderate restrictions
Apply: writes are real → strict restrictions + optional mandatory review

This aligns with the four-phase model's safety rationale.

Resources

A resource is a namespaced, independently registered entity representing anything that a plan can reason about or manipulate — git repositories, filesystems, databases, APIs, documents, and more. Resources are first-class citizens in CleverAgents, managed through the agents resource CLI commands and stored in the Resource Registry.

CleverAgents extends the MCP resource concept to support both read AND write operations (MCP resources are read-only). Unlike MCP's flat resource model, CleverAgents resources form a directed acyclic graph (DAG) with parent/child relationships, support physical vs virtual distinction for content identity tracking, and are governed by a resource type system that constrains their structure and behavior.

Resources are registered independently of projects. Projects link to resources from the Resource Registry — a resource can be linked to multiple projects, enabling shared resources across teams and workflows.

What a Resource Is

A resource has:

Name and namespace: Resources follow the same <namespace>/<name> naming convention as actors, tools, skills, and other entities (e.g., local/api-repo, cleverthis/staging-db).
Resource type: Every resource has a type (e.g., git, fs-mount, git-branch, fs-file) that determines its properties, CLI arguments, allowed parent/child relationships, sandbox strategy, and handler implementation.
Physical or virtual nature: Resources are either physical (a specific, concrete manifestation) or virtual (an abstract identity linking equivalent physical resources). This is determined by the resource type.
Value/properties: Type-specific properties (a file path, a URL, a connection string, a commit hash, etc.).
Parent/child relationships: Resources form a DAG. A resource can have multiple parents and multiple children, subject to type constraints.
Capabilities: Whether the resource is readable, writable, sandboxable, and checkpointable.

Resource Types

A resource type is a schema-level definition that constrains a category of resources. Resource types define:

CLI arguments: What arguments agents resource add <type> accepts (for user-addable types), including which are required vs optional and validation rules.
Physical or virtual: Whether instances of this type are physical or virtual resources.
Allowed parent types: What resource types are valid parents.
Allowed child types: What resource types are valid children, and whether they are auto-discovered or manually linkable.
Auto-discovery behavior: What child resources are automatically created when an instance of this type is registered (e.g., registering a git-checkout resource auto-discovers a git child and an fs-directory child for the worktree root; the git child in turn auto-discovers remotes, branches, commits, and tree entries).
User addable: Whether users can create instances of this type directly via agents resource add <type>. Types with user_addable: false are only generated as auto-discovered children of other resources.
Sandbox strategy: The default sandboxing approach for instances of this type.
Handler: The resource handler implementation that provides read/write/sandbox/checkpoint operations.

Built-in Resource Types

Built-in types are organized into three layers: git (version control structure), git-checkout (a composition that bridges git metadata with a local directory), and filesystem (physical files on disk). Virtual types link equivalent physical resources across these layers through content/identity matching. There are 24 built-in types total (15 physical + 9 virtual), of which 4 are user-addable (git-checkout, git, fs-mount, fs-directory).

Each table below includes the full parent/child relationship constraints. Allowed Parents lists what types may be a parent of this type, with cardinality (how many parents of that type are allowed) and whether the relationship is required or optional. Allowed Children lists what types may be children, with cardinality and whether they are required or optional. 0..* means zero or more, 1 means exactly one (required), 0..1 means zero or one (optional).

Physical types — Git layer (version control structure — every instance is a concrete manifestation in a specific repository):

Type	User Addable	Sandbox	Allowed Parents	Allowed Children	Description
`git`	yes	`none`	`git-checkout` (0..1, optional)	`git-remote` (0.., optional), `git-branch` (0.., optional), `git-tag` (0.., optional), `git-commit` (0.., optional), `git-stash` (0.., optional), `git-submodule` (0.., optional)	A git repository — the object database, refs, and full history. Accessible via a local `.git` directory path or a remote URL. Every `git` resource is a specific, concrete repo instance (local or hosted on a remote server).
`git-remote`	no	`none`	`git` (1, required)	(none)	A remote URL configured on a git repo (e.g., `origin → https://github.com/org/repo`). Auto-discovered child of `git`. Optionally linked as a child of a `remote` virtual resource when the same URL appears in multiple repos.
`git-branch`	no	(inherits)	`git` (1, required)	`git-commit` (0..*, optional)	A named branch ref (e.g., `main`, `feature/auth`). Auto-discovered child of `git`. Optionally linked as a child of a `branch` virtual resource when the same branch name + HEAD exists in multiple repos.
`git-tag`	no	(inherits)	`git` (1, required)	(none)	A tag ref — lightweight or annotated (e.g., `v1.0.0`). Auto-discovered child of `git`. Optionally linked as a child of a `tag` virtual resource when the same tag name + target exists in multiple repos.
`git-commit`	no	(inherits)	`git-branch` (1..*, required), `git` (1, required)	`git-tree` (1, required)	A specific commit object. Auto-discovered child of `git-branch` (a commit can belong to multiple branches). Each commit contains exactly one root `git-tree`. Also a direct child of `git` for ancestry traversal. Optionally linked as a child of a `commit` virtual resource when the same commit hash exists in multiple repos (e.g., shared history between fork and upstream).
`git-tree`	no	(inherits)	`git-commit` (1..*, required)	`git-tree-entry` (0.., optional), `git-tree` (0.., optional)	A tree object — a directory listing at a specific commit. Each tree contains entries (blobs and subtrees). Auto-discovered child of `git-commit`. Trees are recursive: a tree can contain subtrees as children. Optionally linked as a child of a `tree` virtual resource when the same tree hash exists across commits/repos.
`git-tree-entry`	no	(inherits)	`git-tree` (1, required)	(none)	A blob entry in a tree — a specific file's content at a specific path and mode. Auto-discovered child of `git-tree`. Represents the leaf of git's content-addressable storage. Optionally linked as a child of a `file` virtual resource when byte-identical content with the same name and permissions exists in the filesystem layer.
`git-stash`	no	(inherits)	`git` (1, required)	(none)	A stash entry (e.g., `stash@{0}`). Auto-discovered child of `git`. Represents work-in-progress saved via `git stash`.
`git-submodule`	no	(inherits)	`git` (1, required)	(none)	A submodule reference — a pointer to another git repository at a specific commit and path. Auto-discovered child of `git`. Optionally linked as a child of a `submodule` virtual resource when the same submodule URL + path exists in multiple repos.

Physical types — Git checkout (composition: git metadata + local worktree directory):

Type	User Addable	Sandbox	Allowed Parents	Allowed Children	Description
`git-checkout`	yes	`git_worktree`	(none — always a top-level resource)	`git` (1, required), `fs-directory` (1, required)	A locally checked-out git repository. The composition type — auto-discovers a `git` child (the repo's object database, branches, tags, commits, trees, and remotes) and an `fs-directory` child (the worktree root directory, e.g., `/home/user/projects/my-app`). Most users register this type. The worktree root IS a directory, not a mount point, so git-checkout composes with `fs-directory` directly.

Physical types — Filesystem layer (files on disk, used by git checkouts and standalone directories alike):

Type	User Addable	Sandbox	Allowed Parents	Allowed Children	Description
`fs-mount`	yes	`copy_on_write`	(none — always a top-level resource)	`fs-directory` (1, required)	A physical mount point on the local system (e.g., `/mnt/data`, `/home`). Represents the mount itself — the filesystem type (ext4, btrfs, etc.) is a property. The root directory is a required auto-discovered `fs-directory` child. Used for registering entire mount points or storage volumes.
`fs-directory`	yes	`copy_on_write`	`git-checkout` (0..1, optional), `fs-mount` (0..1, optional), `fs-directory` (0..1, optional)	`fs-directory` (0.., optional), `fs-file` (0.., optional), `fs-symlink` (0.., optional), `fs-hardlink` (0.., optional)	A directory on the filesystem. Can be the root child of `fs-mount` (mount point root), the worktree root child of `git-checkout`, a subdirectory child of another `fs-directory`, or a standalone user-registered directory. Optionally linked as a child of a `directory` virtual resource when equivalent directory content exists elsewhere. When user-addable, accepts `--path` flag.
`fs-file`	no	(inherits)	`fs-directory` (1, required)	(none)	A regular file on the local filesystem. Auto-discovered child of `fs-directory`. Optionally linked as a child of a `file` virtual resource when byte-identical content with the same name and permissions exists elsewhere (in another `fs-file` or a `git-tree-entry`).
`fs-symlink`	no	(inherits)	`fs-directory` (1, required)	(none)	A symbolic link on the local filesystem. Auto-discovered child of `fs-directory`. Optionally linked as a child of a `symlink` virtual resource when a symlink with the same name and target exists elsewhere.
`fs-hardlink`	no	(inherits)	`fs-directory` (1, required)	(none)	A hard link on the local filesystem — a file with link count > 1. Auto-discovered child of `fs-directory`. The system tracks hard link relationships by inode to avoid treating the same underlying data as distinct resources.

Virtual types (abstract identity types that link equivalent physical resources — never user-addable, no sandbox):

Virtual types use simple names that mirror their physical counterparts. A virtual resource answers the question: "where else does this same thing exist?" Two physical resources share a virtual parent when they are equivalent by the virtual type's criteria (same content, same name, same permissions, same hash, etc.).

Type	Allowed Children	Description
`file`	`fs-file` (0.., optional), `git-tree-entry` (0.., optional)	Cross-layer file identity. Links physical `fs-file` and `git-tree-entry` resources that represent the same file — identical content bytes, filename, and permissions. Answers: "this file in the working tree and this blob in git's tree are the same file."
`directory`	`fs-directory` (0.., optional), `git-tree` (0.., optional)	Cross-layer directory identity. Links physical `fs-directory` and `git-tree` resources whose recursive contents are equivalent. Answers: "this directory on disk matches this tree object in git."
`symlink`	`fs-symlink` (0.., optional), `git-tree-entry` (0.., optional)	Cross-layer symlink identity. Links physical `fs-symlink` and `git-tree-entry` (mode 120000) resources with the same name and target.
`commit`	`git-commit` (0..*, optional)	Cross-repo commit identity. Links `git-commit` resources across different repos that share the same commit hash — typically a fork and its upstream. Answers: "this commit exists in both repos."
`branch`	`git-branch` (0..*, optional)	Cross-repo branch identity. Links `git-branch` resources across different repos with the same branch name and HEAD commit hash.
`tag`	`git-tag` (0..*, optional)	Cross-repo tag identity. Links `git-tag` resources across different repos with the same tag name and target object.
`remote`	`git-remote` (0..*, optional)	Cross-repo remote identity. Links `git-remote` resources across different repos that point to the same URL. Answers: "these repos share the same upstream."
`submodule`	`git-submodule` (0..*, optional)	Cross-repo submodule identity. Links `git-submodule` resources across different repos with the same submodule URL and path.
`tree`	`git-tree` (0..*, optional)	Cross-repo/cross-commit tree identity. Links `git-tree` resources across different commits or repos that have the same tree hash — identical directory structure and contents.

Key design notes:

Virtual types are never user-addable — they are created and maintained automatically by the system when equivalent physical resources are detected.
Virtual types have no sandbox strategy because they represent abstract identities, not concrete locations. Tools always operate on the physical children.
Physical types list virtual parents in their Allowed Parents column (via the "optionally linked" descriptions). For example, an fs-file can be linked as a child of a file virtual resource when its content matches a git-tree-entry. This is how the DAG connects physical and virtual layers.
git represents a specific git repository instance — whether hosted remotely (e.g., on GitHub's servers) or locally (a .git directory on disk). It is physical because it is a concrete manifestation that exists somewhere, not an abstract identity. A git resource can be created from a remote URL alone (accessing the object database via the git protocol) or from a local .git directory.
git-checkout is the type most users register for repos they've cloned. It composes a git child (repo metadata) and an fs-directory child (the worktree root directory). The worktree root is a directory on an existing filesystem — NOT a separate mount point — so git-checkout links directly to fs-directory, not fs-mount. This means the worktree's files use the same fs-directory and fs-file types regardless of how they were created.
git-commit has a git-tree child (the root tree object), which in turn has git-tree-entry and nested git-tree children. This properly models git's internal object structure: commits point to trees, trees contain entries (blobs) and subtrees.
fs-mount represents a physical mount point, not a directory. The filesystem type (ext4, btrfs, etc.) is a property on the mount. The root directory is an auto-discovered fs-directory child. Use fs-mount for registering mount points and storage volumes. Use fs-directory (user-addable) for registering arbitrary directories.
fs-directory is user-addable, allowing users to register standalone directories (e.g., a build output folder, a config directory) without wrapping them in an fs-mount. An fs-directory registered standalone or as a child of fs-mount/git-checkout uses the same type and auto-discovers the same fs-file, fs-symlink, fs-hardlink, and nested fs-directory children.
git-tree-entry represents a blob in git's tree — a specific file's content at a specific path and mode. The corresponding file on disk (if checked out) is an fs-file. The file virtual type bridges these two when their content, name, and permissions are identical.
4 user-addable types: git-checkout (local repo), git (remote or local metadata-only), fs-mount (mount point), fs-directory (arbitrary directory).

Built-in Type Hierarchy

The parent-child relationships between built-in resource types form three layers — git structure, git checkout (composition), and filesystem — bridged by virtual identity types:

@startuml
skinparam defaultFontSize 11
skinparam objectFontSize 11
skinparam packageStyle rectangle

package "GIT-CHECKOUT (composition)" as GC #LightBlue {
  object "git-checkout" as gc {
    /home/user/projects/myapp
  }
}

package "GIT STRUCTURE" as GS #LightYellow {
  object "git" as git {
    repo object DB
  }
  object "git-remote" as remote {
    origin
  }
  object "git-tag" as tag {
    v1.0.0
  }
  object "git-submodule" as submod {
    lib/shared
  }
  object "git-branch" as branch {
    main
  }
  object "git-stash" as stash {
    stash@0
  }
  object "git-commit" as commit {
    a1b2c3d
  }
  object "git-tree" as tree {
    e8f1... root
  }
  object "git-tree-entry" as entry1 {
    README.md
  }
  object "git-tree" as subtree {
    src/ subtree
  }
  object "git-tree-entry" as entry2 {
    src/app.ts
  }
  object "git-tree-entry" as entry3 {
    src/main.ts
  }
}

package "FILESYSTEM (worktree)" as FS #LightGreen {
  object "fs-directory" as fsroot {
    worktree root
  }
  object "fs-directory" as srcdir {
    src/
  }
  object "fs-file" as readme {
    README.md
  }
  object "fs-file" as app {
    app.ts
  }
  object "fs-file" as main {
    main.ts
  }
}

package "STANDALONE FS-DIRECTORY" as SFS #Wheat {
  object "fs-directory" as sfs {
    /opt/deploy/myapp
  }
  object "fs-directory" as ssrcdir {
    src/
  }
  object "fs-file" as sreadme {
    README.md
  }
  object "fs-file" as sapp {
    app.ts
  }
  object "fs-file" as smain {
    main.ts
  }
  object "fs-symlink" as symlink {
    link.txt
  }
}

package "STANDALONE FS-MOUNT" as SM #LightCoral {
  object "fs-mount" as mount {
    /mnt/data
  }
  object "fs-directory" as mountroot {
    root: /
  }
}

package "VIRTUAL LAYER (abstract identities)" as VL #Lavender {
  object "file" as vfile {
    app.ts @ sha256:9f8e...
  }
  object "directory" as vdir {
    src/ @ merkle:3d4f...
  }
  object "commit" as vcommit {
    a1b2c3d
  }
  object "branch" as vbranch {
    main @ a1b2c3d
  }
  object "remote" as vremote {
    github.com/org/repo
  }
  object "tree" as vtree {
    e8f1...9d2a
  }
}

gc --> git
gc --> fsroot

mount --> mountroot

git --> remote
git --> tag
git --> submod
git --> branch
git --> stash

branch --> commit
commit --> tree
tree --> entry1
tree --> subtree
subtree --> entry2
subtree --> entry3

fsroot --> srcdir
fsroot --> readme
srcdir --> app
srcdir --> main

sfs --> ssrcdir
sfs --> sreadme
sfs --> symlink
ssrcdir --> sapp
ssrcdir --> smain

app ..> vfile : equivalent
sapp ..> vfile : equivalent
entry2 ..> vfile : equivalent
srcdir ..> vdir : equivalent
ssrcdir ..> vdir : equivalent
subtree ..> vdir : equivalent
commit ..> vcommit : equivalent
branch ..> vbranch : equivalent
remote ..> vremote : equivalent
tree ..> vtree : equivalent
@enduml

Reading the diagram:

Top left: A git-checkout resource decomposes into a git child (left — the repository's full structure) and an fs-directory child (center — the worktree root directory at /home/user/projects/myapp). The worktree root is a directory, not a mount point.
Git structure (left column): The git child contains git-remote (origin), git-tag (v1.0.0), git-submodule (lib/shared), git-stash (stash@{0}), and git-branch (main). The branch contains git-commit objects, each commit contains a root git-tree, and trees contain git-tree-entry (blobs) and nested git-tree (subtrees). This properly models git's internal object structure.
Filesystem (center/right): The worktree's fs-directory contains src/ (an fs-directory), README.md (an fs-file), and files including fs-symlink resources. A standalone fs-directory (/opt/deploy/myapp) with the same structure. A standalone fs-mount (/mnt/data) with a root fs-directory child.
Virtual layer (boxed area): Shows how virtual types link equivalent physical resources:
- A file virtual resource links fs-file and git-tree-entry resources that have the same content, filename, and permissions — bridging the filesystem and git layers.
- A directory virtual resource links fs-directory and git-tree resources with the same recursive content.
- A commit virtual resource links git-commit resources across repos with the same commit hash.
- A branch virtual resource links git-branch resources across repos with the same name and HEAD.
- A remote virtual resource links git-remote resources across repos with the same URL.
- A tree virtual resource links git-tree resources across repos/commits with the same tree hash.

Key separations:

git vs git-checkout: A git resource represents a specific repository instance (local or remote). It can exist without any local directory (created from a remote URL — the repo exists on the remote server). A git-checkout always has both a git child and an fs-directory child — it represents a locally cloned repo with files on disk.
git-tree-entry vs fs-file: A git-tree-entry is a blob entry in git's tree (path + content hash + mode). An fs-file is a physical file on disk. When a repo is checked out, both exist and typically have matching content — the file virtual type links them when content, name, and permissions match.
git-tree vs fs-directory: A git-tree is a tree object in git's object database (a directory listing at a commit). An fs-directory is a physical directory on disk. The directory virtual type links them when their recursive contents match.
git-commit → git-tree → git-tree-entry: This chain properly models git internals. Commits point to a root tree, trees contain entries (blobs) and subtrees. The old design skipped the tree level; the current design preserves it.
fs-mount vs fs-directory: An fs-mount is a mount point (e.g., /mnt/data). The filesystem type (ext4, btrfs, etc.) is a property. The root directory is an fs-directory child. An fs-directory is a directory — it can be a child of fs-mount, git-checkout, or another fs-directory, or it can be registered standalone by the user.
git-checkout composes with fs-directory, not fs-mount: A git checkout's worktree is a directory on an existing filesystem, not a separate mount point. This is why git-checkout's required child is fs-directory (the worktree root), not fs-mount.
Virtual types bridge physical equivalents: file bridges fs-file + git-tree-entry (cross-layer). directory bridges fs-directory + git-tree (cross-layer). commit, branch, tag, remote, submodule, and tree link the same git structural element across different repos.

Concrete Example: A Made-Up Project

Consider a web application called "Acme Dashboard" with three registered resources:

local/acme-app — a checked-out git repo at /home/alice/projects/acme-dashboard (type: git-checkout)
local/acme-upstream — a git repo accessed via remote URL, not cloned (type: git)
local/acme-deploy — a standalone directory at /opt/deploy/acme-dashboard containing a production build snapshot (type: fs-directory)

Registration:

# 1) Checked-out git repo (has local files on disk)
agents resource add git-checkout local/acme-app \
  --path /home/alice/projects/acme-dashboard --branch main

# 2) Git repo via remote URL (no local checkout — metadata only)
agents resource add git local/acme-upstream \
  --url git@github.com:acmecorp/dashboard.git

# 3) Standalone directory (not a git repo — just files on disk)
agents resource add fs-directory local/acme-deploy \
  --path /opt/deploy/acme-dashboard

What gets auto-discovered for each:

local/acme-app (type: git-checkout) discovers two children — a git and an fs-directory (the worktree root):

@startwbs
* local/acme-app\n(git-checkout / physical)
** local/acme-app:repo\n(git / physical)
*** acme-app:repo:origin\n(git-remote)\ngit@github.com:acmecorp/dashboard.git
*** acme-app:repo:v1.0.0\n(git-tag)
*** acme-app:repo:lib/shared\n(git-submodule @ c4d5e6f)
*** acme-app:repo:stash@0\n(git-stash)
*** acme-app:repo:main\n(git-branch)
**** main:a7f3e21\n(git-commit)
***** main:a7f3e21:tree\n(git-tree / root)
****** a7f3e21:README.md\n(git-tree-entry)
****** a7f3e21:package.json\n(git-tree-entry)
****** a7f3e21:src/\n(git-tree / subtree)
******* a7f3e21:src/app.ts\n(git-tree-entry)
******* a7f3e21:src/api.ts\n(git-tree-entry)
******* a7f3e21:src/utils.ts\n(git-tree-entry)
*** acme-app:repo:develop\n(git-branch)
**** develop:b2c4d8e\n(git-commit)
***** develop:b2c4d8e:tree\n(git-tree)
****** b2c4d8e:src/\n(git-tree)
******* b2c4d8e:src/app.ts\n(git-tree-entry)
******* b2c4d8e:src/api.ts\n(git-tree-entry / modified)
** local/acme-app:worktree\n(fs-directory / physical)\n/home/alice/projects/acme-dashboard/
*** worktree:src/\n(fs-directory)
**** worktree:src/app.ts\n(fs-file)
**** worktree:src/api.ts\n(fs-file)
**** worktree:src/utils.ts\n(fs-file)
*** worktree:package.json\n(fs-file)
*** worktree:README.md\n(fs-file)
*** worktree:docs -> ../docs\n(fs-symlink)
@endwbs

The git-checkout cleanly separates two concerns: the git child contains version control structure (remotes, branches, tags, stashes, submodules, commits, trees, and tree entries — git's full object model), while the fs-directory child is the worktree root directory containing the actual files on disk. Note how git's internal structure is fully modeled: git-commit → git-tree (root tree object) → git-tree-entry (blobs) and nested git-tree (subtrees). The worktree root is a directory (fs-directory), not a mount point — git-checkout does not own an fs-mount resource because a git checkout's worktree is just a directory on an existing filesystem. When content matches (as it does for a clean checkout), virtual types link the fs-file and git-tree-entry resources.

local/acme-upstream (type: git, remote URL — NOT checked out) discovers:

@startwbs
* local/acme-upstream\n(git / physical)\ngit@github.com:acmecorp/dashboard.git
** acme-upstream:origin\n(git-remote)
** acme-upstream:v1.0.0\n(git-tag)
** acme-upstream:main\n(git-branch)
*** main:a7f3e21\n(git-commit)
**** main:a7f3e21:tree\n(git-tree)
***** a7f3e21:src/\n(git-tree)
****** a7f3e21:src/app.ts\n(git-tree-entry)
****** a7f3e21:src/api.ts\n(git-tree-entry)
** acme-upstream:develop\n(git-branch)
*** ...\n(remaining structure)
@endwbs

A standalone git resource has full access to branches, tags, commits, trees, and tree entries — everything in the git object database — but no fs-directory child and no fs-file resources. There are no files on the local disk (the repo exists on GitHub's servers). Tools that need local file access cannot bind to it.

This is the key difference from git-checkout: a git resource represents a specific repo instance. Plans can reason about history, diffs between branches, remote relationships — without a local clone. A git-checkout adds the local worktree directory on top.

local/acme-deploy (type: fs-directory, standalone) discovers:

@startwbs
* local/acme-deploy\n(fs-directory / physical)\n/opt/deploy/acme-dashboard/
** acme-deploy:src/\n(fs-directory)
*** acme-deploy:src/app.ts\n(fs-file)
*** acme-deploy:src/api.ts\n(fs-file)
*** acme-deploy:src/utils.ts\n(fs-file)
** acme-deploy:package.json\n(fs-file)
** acme-deploy:README.md\n(fs-file)
@endwbs

A standalone fs-directory — no git metadata, no branches, no commits, no tree entries. Just a directory containing files and subdirectories. Uses the same fs-directory and fs-file types as the git checkout's worktree root.

Virtual resource linking across all three:

After all three resources are registered, the system detects equivalent physical resources and creates virtual parents to link them:

@startuml
skinparam defaultFontSize 10
skinparam objectFontSize 10
skinparam packageStyle rectangle
left to right direction

package "PHYSICAL: local/acme-app" as P1 #LightBlue {
  object "fs-directory" as acmeWtSrc {
    worktree:src/
  }
  object "fs-file" as acmeWtApp {
    worktree:src/app.ts
  }
  object "fs-file" as acmeWtUtils {
    worktree:src/utils.ts
  }
  object "fs-file" as acmeWtApi {
    worktree:src/api.ts
  }
  object "git-tree" as acmeGitSrc {
    main:a7f3e21:src/
  }
  object "git-tree-entry" as acmeGitApp {
    main:src/app.ts
  }
  object "git-tree-entry" as acmeGitUtils {
    main:src/utils.ts
  }
  object "git-tree-entry" as acmeGitApi {
    main:src/api.ts
  }
  object "git-commit" as acmeCommit {
    main:a7f3e21
  }
  object "git-branch" as acmeBranch {
    main
  }
  object "git-tag" as acmeTag {
    v1.0.0
  }
  object "git-remote" as acmeRemote {
    origin
  }
  object "git-tree" as acmeTree {
    main:a7f3e21:tree
  }
  object "git-submodule" as acmeSubmod {
    lib/shared
  }
}

package "PHYSICAL: local/acme-deploy" as P2 #LightGreen {
  object "fs-directory" as deploySrc {
    src/
  }
  object "fs-file" as deployApp {
    src/app.ts
  }
  object "fs-file" as deployUtils {
    src/utils.ts
  }
  object "fs-file" as deployApi {
    src/api.ts
  }
}

package "PHYSICAL: local/acme-upstream" as P3 #LightYellow {
  object "git-tree" as upstreamSrc {
    main:a7f3e21:src/
  }
  object "git-tree-entry" as upstreamApp {
    main:src/app.ts
  }
  object "git-tree-entry" as upstreamUtils {
    main:src/utils.ts
  }
  object "git-tree-entry" as upstreamApi {
    main:src/api.ts
  }
  object "git-commit" as upstreamCommit {
    main:a7f3e21
  }
  object "git-branch" as upstreamBranch {
    main
  }
  object "git-tag" as upstreamTag {
    v1.0.0
  }
  object "git-remote" as upstreamRemote {
    origin
  }
  object "git-tree" as upstreamTree {
    main:a7f3e21:tree
  }
}

package "VIRTUAL LAYER\n(auto-created by equivalence)" as VL #Lavender {
  object "directory" as vDir {
    src/ (merkle:3d4f...)
  }
  object "file" as vAppTs {
    app.ts (sha256:9f8e...)
  }
  object "file" as vUtilsTs {
    utils.ts (sha256:a2b1...)
  }
  object "file" as vApiTs {
    api.ts (sha256:e1d3...)
  }
  object "commit" as vCommit {
    a7f3e21
  }
  object "branch" as vBranch {
    main @ a7f3e21
  }
  object "tag" as vTag {
    v1.0.0
  }
  object "remote" as vRemote {
    github.com:acmecorp/dashboard.git
  }
  object "tree" as vTree {
    e8f1...9d2a
  }
  object "submodule" as vSubmod {
    lib/shared
  }
}

acmeWtSrc ..> vDir
deploySrc ..> vDir
acmeGitSrc ..> vDir
upstreamSrc ..> vDir

acmeWtApp ..> vAppTs
deployApp ..> vAppTs
acmeGitApp ..> vAppTs
upstreamApp ..> vAppTs

acmeWtUtils ..> vUtilsTs
deployUtils ..> vUtilsTs
acmeGitUtils ..> vUtilsTs
upstreamUtils ..> vUtilsTs

acmeWtApi ..> vApiTs
deployApi ..> vApiTs
acmeGitApi ..> vApiTs
upstreamApi ..> vApiTs

note "NOT linked: develop:b2c4d8e:src/api.ts\n(different content on develop branch)" as N1

acmeCommit ..> vCommit
upstreamCommit ..> vCommit

acmeBranch ..> vBranch
upstreamBranch ..> vBranch

acmeTag ..> vTag
upstreamTag ..> vTag

acmeRemote ..> vRemote
upstreamRemote ..> vRemote

acmeTree ..> vTree
upstreamTree ..> vTree

acmeSubmod ..> vSubmod
@enduml

How the directory virtual type works:

The directory virtual resource for src/ exists because the src/ directory has identical recursive content across multiple physical locations. Its children include both fs-directory resources (physical directories on disk) and git-tree resources (tree objects in git's object database). The system detects directory equivalence by computing a Merkle hash over the sorted child content hashes. If someone adds a file to the deploy directory but not the git checkout's worktree, the Merkle hashes diverge, and local/acme-deploy:src/ is unlinked from the directory virtual parent.

How the file virtual type works:

The file virtual type links physical resources that represent the same file — identical content bytes, filename, and permissions. It bridges across layers: an fs-file on disk and a git-tree-entry in git's tree are linked when they have matching content. This is the primary cross-layer bridge. When content diverges (e.g., an uncommitted edit), the virtual link is broken.

How commit works across repos:

When two git resources share history (e.g., a fork and its upstream), the same commit hash will appear in both repos' branches. The commit virtual type links these — the commit object a7f3e21 in the local repo and a7f3e21 in the upstream repo are the same commit, and the virtual parent captures this identity.

Divergence scenario:

If a developer edits src/api.ts in the deploy directory (/opt/deploy/acme-dashboard/src/api.ts), the system detects the content hash change and:

Unlinks local/acme-deploy:src/api.ts from file: api.ts (sha256:e1d3...8a9b) (content no longer matches).
Unlinks local/acme-deploy:src/ from directory: src/ (merkle:3d4f...a2b1) (directory contents no longer identical — the Merkle hash has changed).
The git checkout's worktree files and git-tree-entry resources remain linked (their content hasn't changed).
If the edit makes the deploy file match some other known content hash, a new virtual link may be created.

Additional resource types (databases, APIs, cloud infrastructure, etc.) can be added as custom resource types via agents resource type add.

Custom Resource Types

Custom resource types are defined in YAML configuration files and registered via agents resource type add. Once registered, a custom type automatically becomes available as a new subcommand under agents resource add.

# File: resource-types/database.yaml
cleveragents:
  version: "3.0"

resource_type:
  name: local/database
  description: "A SQL database (PostgreSQL, MySQL, SQLite, etc.)"
  physical_or_virtual: physical
  user_addable: true

  # CLI arguments for `agents resource add local/database`
  cli_arguments:
    - name: connection-string
      type: string
      required: true
      description: "Database connection string (e.g., postgresql://host/dbname)"
      validation:
        pattern: "^(postgresql|mysql|sqlite)://"
    - name: schema
      type: string
      required: false
      description: "Default schema to use"
    - name: read-only
      type: boolean
      required: false
      default: false
      description: "Whether the database should be treated as read-only"

  # Sandbox and handler
  sandbox_strategy: transaction_rollback
  handler: DatabaseHandler
  checkpointable: true

  # Allowed parent types (empty means can be top-level)
  allowed_parent_types: []

  # Child types
  child_types:
    - type: local/db-schema
      auto_discover: true
      manual_link: false
      description: "Discovered database schemas"
    - type: local/db-table
      auto_discover: true
      manual_link: false
      description: "Discovered tables within schemas"

  # Capabilities
  capabilities:
    readable: true
    writable: true
    sandboxable: true
    checkpointable: true

When this type is registered:

agents resource type add local/database --config ./resource-types/database.yaml
# Now available: agents resource add local/database <NAME> --connection-string CONN [--schema SCHEMA] [--read-only]

The user_addable field determines whether the type appears as a subcommand. Types with user_addable: false are only auto-generated as children — for example, git-remote, git-branch, git-commit, and git-tree-entry are never created directly by users but are discovered when a git (or git-checkout) resource is registered.

The Resource DAG

Resources form a directed acyclic graph (DAG), not a simple tree. A resource can have multiple parents and multiple children, subject to type constraints. The diagram below shows how a git-checkout, a standalone git repo (remote), a standalone fs-directory, and virtual resources interconnect:

@startuml
skinparam defaultFontSize 10
skinparam objectFontSize 10
skinparam packageStyle rectangle

package "GIT-CHECKOUT: local/app" as GCO #LightBlue {
  object "git-checkout" as gco {
    local/app
  }
  object "git" as gcoGit {
    local/app:repo
  }
  object "git-remote" as gcoRemote {
    origin
  }
  object "git-tag" as gcoTag {
    v1.0.0
  }
  object "git-branch" as gcoBranch {
    main
  }
  object "git-commit" as gcoCommit {
    a1b2c3d
  }
  object "git-tree" as gcoTree {
    e8f1... root
  }
  object "git-tree-entry" as gcoEntry1 {
    README.md
  }
  object "git-tree" as gcoSubtree {
    src/
  }
  object "git-tree-entry" as gcoEntry2 {
    src/app.ts
  }
  object "git-tree-entry" as gcoEntry3 {
    src/main.ts
  }
  object "fs-directory" as gcoFs {
    local/app:worktree
  }
  object "fs-directory" as gcoSrcDir {
    src/
  }
  object "fs-file" as gcoReadme {
    README.md
  }
  object "fs-file" as gcoApp {
    app.ts
  }
  object "fs-file" as gcoMain {
    main.ts
  }
}

package "GIT (remote): local/upstream" as GR #LightYellow {
  object "git" as gr {
    local/upstream
  }
  object "git-remote" as grRemote {
    origin
  }
  object "git-tag" as grTag {
    v1.0.0
  }
  object "git-branch" as grBranch {
    main
  }
  object "git-commit" as grCommit {
    a1b2c3d
  }
  object "git-tree" as grTree {
    e8f1... root
  }
  object "git-tree-entry" as grEntry1 {
    README.md
  }
  object "git-tree" as grSubtree {
    src/
  }
  object "git-tree-entry" as grEntry2 {
    src/app.ts
  }
  object "git-tree-entry" as grEntry3 {
    src/main.ts
  }
}

package "STANDALONE FS-DIRECTORY: local/deploy" as SFD #LightGreen {
  object "fs-directory" as sfd {
    /opt/deploy/myapp
  }
  object "fs-directory" as sfdSrcDir {
    src/
  }
  object "fs-file" as sfdReadme {
    README.md
  }
  object "fs-file" as sfdApp {
    app.ts
  }
  object "fs-file" as sfdMain {
    main.ts
  }
}

package "VIRTUAL LAYER" as VL #Lavender {
  object "file" as vFile {
    app.ts@v1
  }
  object "directory" as vDir {
    src/@v1
  }
  object "commit" as vCommit {
    a1b2c3d
  }
  object "branch" as vBranch {
    main@a1b...
  }
  object "tag" as vTag {
    v1.0.0
  }
  object "remote" as vRemote {
    github.com/org/repo
  }
  object "tree" as vTree {
    e8f1...9d2a
  }
}

' Physical hierarchy
gco --> gcoGit
gco --> gcoFs
gcoGit --> gcoRemote
gcoGit --> gcoTag
gcoGit --> gcoBranch
gcoBranch --> gcoCommit
gcoCommit --> gcoTree
gcoTree --> gcoEntry1
gcoTree --> gcoSubtree
gcoSubtree --> gcoEntry2
gcoSubtree --> gcoEntry3
gcoFs --> gcoSrcDir
gcoFs --> gcoReadme
gcoSrcDir --> gcoApp
gcoSrcDir --> gcoMain

gr --> grRemote
gr --> grTag
gr --> grBranch
grBranch --> grCommit
grCommit --> grTree
grTree --> grEntry1
grTree --> grSubtree
grSubtree --> grEntry2
grSubtree --> grEntry3

sfd --> sfdSrcDir
sfd --> sfdReadme
sfdSrcDir --> sfdApp
sfdSrcDir --> sfdMain

' Virtual equivalence links
gcoApp ..> vFile
sfdApp ..> vFile
gcoEntry2 ..> vFile
grEntry2 ..> vFile
gcoSrcDir ..> vDir
sfdSrcDir ..> vDir
gcoSubtree ..> vDir
grSubtree ..> vDir
gcoCommit ..> vCommit
grCommit ..> vCommit
gcoBranch ..> vBranch
grBranch ..> vBranch
gcoTag ..> vTag
grTag ..> vTag
gcoRemote ..> vRemote
grRemote ..> vRemote
gcoTree ..> vTree
grTree ..> vTree
@enduml

Key properties of the DAG:

Multiple parents: A git-tree-entry has a git-tree parent (git structure) and potentially a file virtual parent (content identity). An fs-file has an fs-directory parent (filesystem hierarchy) and potentially a file virtual parent. An fs-directory can be a child of git-checkout (as its worktree root), a child of fs-mount (as the mount root), a child of another fs-directory (as a subdirectory), a child of a directory virtual (identity), or a standalone user-registered resource.
Multiple children: A git-checkout has a git child and an fs-directory child. A git resource has git-remote, git-branch, git-tag, git-stash, git-submodule, and git-commit children. A git-commit has a git-tree child. A git-tree has git-tree-entry and nested git-tree children.
Cycles are forbidden: The graph is always a DAG. The system validates this when links are created.
Type constraints: Not any resource can be a child of any other — the parent's resource type defines which child types are allowed (see the Allowed Parents / Allowed Children columns in the built-in types tables).
Cross-layer bridge: Virtual resources link equivalent physical resources from different layers (git structure, filesystem, different repos). The file virtual type bridges fs-file + git-tree-entry. The directory virtual type bridges fs-directory + git-tree. The commit, branch, tag, remote, submodule, and tree virtual types link the same git structural element across different repositories.

Physical vs Virtual Resources

Resources are either physical or virtual, a distinction determined by their resource type.

Physical resources are specific, concrete manifestations. Each physical resource is a particular instance that exists somewhere — a file at a particular path on a particular machine, a git repository at a particular URL on a particular server, a commit in a particular repo. Physical resources can be directly read and written by tools. Most resources are physical.

Virtual resources represent an abstract identity that links equivalent physical resources. They answer the question: "where else does this same thing exist?" A file virtual resource links all the physical fs-file and git-tree-entry resources that have the same content, filename, and permissions. A commit virtual resource links git-commit resources across repos that share the same commit hash. Virtual resources have no location of their own and cannot be directly read or written.

Rules for the physical/virtual boundary:

The children of a virtual resource can be physical resources, other virtual resources, or a combination of both.
A physical resource's parents can be either physical or virtual resources.
Not all physical resources need a virtual parent. Virtual resource linking is optional and only applies when equivalence tracking is meaningful.

Equivalence linking:

Two physical resources share a virtual parent when they are equivalent by the virtual type's criteria. Each virtual type has its own equivalence semantics:

file: Physical files (fs-file or git-tree-entry) share a file parent when they have the same content bytes (SHA-256), the same filename, and the same permissions. This is the primary cross-layer bridge — it links filesystem files with git blob entries. Example: local/app:worktree:src/main.py (an fs-file) and local/app:repo:main:a1b...:src/main.py (a git-tree-entry) both have the same content in a clean checkout, so they share a file virtual parent.
directory: Physical directories (fs-directory) and git trees (git-tree) share a directory parent when their full recursive contents are equivalent. This bridges the filesystem and git layers — the src/ directory on disk and the src/ subtree in git's tree object can be linked when their contents match.
symlink: Physical symlinks (fs-symlink) and git tree entries with symlink mode (git-tree-entry mode 120000) share a symlink parent when they have the same name and target.
commit: Physical commits (git-commit) in different repos share a commit parent when they have the same commit hash. This is common when repos share history (e.g., a fork and its upstream).
branch: Physical branches (git-branch) in different repos share a branch parent when they have the same name and the same HEAD commit hash. A push or local commit on one repo causes divergence.
tag: Physical tags (git-tag) in different repos share a tag parent when they have the same tag name and target object.
remote: Physical remotes (git-remote) in different repos share a remote parent when they point to the same URL. Answers: "these repos share the same upstream."
submodule: Physical submodules (git-submodule) in different repos share a submodule parent when they have the same submodule URL and path.
tree: Physical tree objects (git-tree) in different commits or repos share a tree parent when they have the same tree hash — identical directory structure and contents.

Divergence detection:

When a physical resource's content changes (e.g., a file is edited, a directory gains a new file, a branch advances), the system detects that it may no longer match its virtual parent's identity. At that point:

If the edit causes the physical resource to diverge from all other physical siblings under the same virtual parent, the physical resource is unlinked from that virtual parent.
If the edit makes it match a different virtual resource's identity, it may be re-linked.
Content equivalence is tracked via content hashing: SHA-256 for files, Merkle hashes for directories, tree hashes for git trees, commit hashes for commits, HEAD+name for branches, name+target for tags, URL for remotes.
Cascading divergence: When a file link breaks, the parent directory virtual resource is also re-evaluated (since its identity depends on all child identities).

This enables powerful queries like:

"What physical locations exist for this file content?" → Find all physical resources sharing the file virtual parent.
"What tools can edit this file?" → Find all tools with resource bindings compatible with the physical resource types.
"Has this file been modified in any location?" → Check if all physical siblings still share the same file virtual parent.
"Are these two repos in sync?" → Check if their branches share a branch virtual parent.
"Which directories are identical across deployments?" → Find directory virtual resources with multiple physical children.
"What submodules are shared across projects?" → Find submodule virtual resources with multiple physical children.

Resource Registration (CLI)

Resources are created via agents resource add <type> with type-specific arguments. Auto-discovered children are created automatically:

# Register a checked-out git repository (most common)
agents resource add git-checkout local/api-repo --path /home/user/projects/api-service --branch main
# Auto-discovers: git child (repo metadata, remotes, branches, commits, tree entries)
#                 + fs-directory child (worktree root directory, subdirectories, files)

# Register a git repo via remote URL (no local checkout — exists on remote server)
agents resource add git local/upstream --url git@github.com:org/upstream.git
# Auto-discovers: remotes, branches, tags, commits, trees, tree entries, stashes, submodules
#                 (no fs-directory — not checked out locally)

# Register a standalone directory (not a git repo — just files on disk)
agents resource add fs-directory local/docs --path /opt/docs/api-reference
# Auto-discovers: subdirectories, files, symlinks, hardlinks

# Register a standalone filesystem mount (entire volume)
agents resource add fs-mount local/data-volume --mount-path /mnt/data
# Auto-discovers: root fs-directory, subdirectories, files, symlinks, hardlinks

# Link resources to projects (resources must be registered first)
agents project link-resource --project local/api-service --resource local/api-repo
agents project link-resource --project local/api-service --resource local/docs --read-only

Auto-Discovery

When a resource is registered, its resource type's handler auto-discovers child resources. This process:

Scans the resource to identify children (e.g., a git-checkout handler creates a git child and an fs-directory child for the worktree root; a git handler lists remotes, branches, tags, commits, stashes, and submodules; a git-commit handler creates a root git-tree child; a git-tree handler lists tree entries and subtrees; an fs-mount handler creates a root fs-directory and discovers its contents; an fs-directory handler discovers subdirectories, files, symlinks, and hardlinks).
Creates child resource records in the Resource Registry with auto-generated names (e.g., local/api-repo:repo for the git child, local/api-repo:worktree for the worktree root fs-directory child, local/api-repo:repo:main for a branch).
Reuses existing resources: If a discovered child matches an already-registered resource (same type + same value/location), the existing resource is linked as a child rather than creating a duplicate. For example, if local/docs (an fs-directory resource at /home/user/projects/api-service) is already registered and the git-checkout handler discovers its worktree root at the same path, it links to the existing local/docs resource instead of creating a new one.
Links virtual resources: When auto-discovery detects that a physical resource's content matches an existing virtual resource (via content hashing), it links the physical resource as a child of the virtual resource.

Auto-discovered children are marked as auto: true in the DAG, distinguishing them from manually linked children. Auto-discovered links cannot be manually unlinked (they are managed by the handler), while manually created links can be freely managed.

Auto-discovery runs:

At registration time (agents resource add)
On refresh (when the system detects changes, e.g., new commits, new files)
On demand (when a tool accesses the resource and the handler detects staleness)

Resource Capabilities

Each resource declares its capabilities, derived from its resource type:

Capability	Description
`readable`	Whether the resource can be read
`writable`	Whether the resource can be modified
`sandboxable`	Whether the resource supports sandbox isolation
`checkpointable`	Whether the resource supports checkpoint/rollback

These capabilities are used by the tool execution flow to validate that a tool's resource binding is compatible — a tool declaring access: read_write on a resource slot cannot be bound to a read-only resource.

Resource Registry

CleverAgents maintains a Resource Registry — a persistent catalog of all registered resources and their DAG relationships:

@startuml
skinparam classAttributeIconSize 0
skinparam classFontSize 13
skinparam defaultFontSize 12

class ResourceRegistry {
  - resourceIndex : Map<String, ResourceRecord>
  - typeIndex : Map<String, ResourceTypeRecord>
  --
  + add(type, name, properties) : ResourceRecord
  + upgrade(name, properties) : ResourceRecord
  + remove(name) : void
  + lookup(name) : ResourceRecord
  + list(filters) : ResourceRecord[]
  + tree(name, depth) : DAG_subtree
  + link_child(parent, child) : void
  + unlink_child(parent, child) : void
  + refresh(name) : void
  + find_by_content(hash) : ResourceRecord[]
  + find_virtual_parent(resource) : ResourceRecord
}

class ResourceRecord {
  + name : String
  + type : String
  + physical_or_virtual : PhysVirt
  + properties : Map<String, Object>
  + capabilities : Capabilities
  + parents : List<ResourceRecord>
  + children : List<ResourceRecord>
  + content_hash : String
  + linked_projects : List<String>
  + created_at : DateTime
  + updated_at : DateTime
}

class ResourceTypeRecord {
  + name : String
  + description : String
  + source : String
  + physical_or_virtual : PhysVirt
  + user_addable : Boolean
  + cli_arguments : List<CLIArgument>
  + allowed_parent_types : List<String>
  + child_types : Map<String, ChildTypeConfig>
  + sandbox_strategy : String
  + handler : String
  + capabilities : Capabilities
  + config_path : String
}

enum PhysVirt {
  physical
  virtual
}

ResourceRegistry "1" *-- "0..*" ResourceRecord : indexes resources >
ResourceRegistry "1" *-- "0..*" ResourceTypeRecord : indexes types >
ResourceRecord --> PhysVirt
ResourceTypeRecord --> PhysVirt

note right of ResourceRegistry
  **Populated by:**
  - agents resource add CLI
  - Auto-discovery during registration
  - Content-identity linking

  **Consumed by:**
  - Tool binding resolution
  - Sandbox creation
  - Change tracking
  - Project linking
  - Plan validation
end note
@enduml

The Resource Registry persists in the database (local SQLite or server). It works alongside the Tool Registry and Skill Registry.

Resource Sandbox Strategy

Each resource defines its own sandbox strategy, determined by its resource type. This is critical because:

The same resource may be accessed through different tools and skills
Different resource types require different sandboxing approaches
Some resources cannot be sandboxed at all

Resource Type	Sandbox Strategy	Rollback Mechanism
`git-checkout`	`git_worktree`	Git reset/checkout
`git`	`none`	N/A (represents a repo instance — not directly sandboxable)
`fs-mount`	`copy_on_write` or `overlay`	Restore from snapshot
`fs-directory`	`copy_on_write`	Restore from snapshot
Custom database types	`transaction_rollback`	Transaction rollback
Custom API types	`none` (often not sandboxable)	N/A

The sandbox strategy is inherited by child resources from their parent unless the child type defines its own. For example, git-branch, git-commit, git-tree, and git-tree-entry all inherit from their git ancestor. fs-file, fs-symlink, and fs-hardlink inherit from their fs-directory parent.

Lazy Sandboxing

Resources are sandboxed lazily when accessed, not upfront. This is different from indexing — resources are indexed immediately when registered, but sandboxes are only created when execution needs to modify a resource:

A project may link many resources (e.g., git repo + databases + cloud accounts)
A plan may only need to modify one resource
Only the accessed resources are sandboxed
Each plan/child plan has its own sandbox containing only edited resources

This is efficient for large projects where most resources remain untouched.

Resource Access Tracking

The system tracks which tools access which resources through the tool-resource binding system. This tracking happens at multiple levels:

Declaration-time: Tool YAML declares resource slots with type and access mode (see Resource Bindings in the Tools section).
Activation-time: When a tool is activated for a plan, its resource slots are bound to specific resources. The system records these bindings.
Execution-time: Every tool invocation logs which bound resources were actually accessed, what operations were performed (read/write/delete), and what paths or objects were touched.

This enables:

Accurate sandbox scoping: Only sandbox resources that will actually be modified.
Rollback feasibility analysis: Know exactly which resources were modified and whether they support rollback.
Security auditing: Complete record of which tools accessed which resources and how.
Cross-resource impact analysis: Determine if changes to a resource affect tools bound to sibling or child resources.
Virtual resource consistency: Detect when a physical resource diverges from its virtual parent.

Unified Resource Abstraction Layer

CleverAgents provides a unified abstraction that allows tools to work with any resource type through a consistent interface. This enables:

Resource-agnostic tools: A tool like read_content(path) works whether the path refers to a file, database record, or API endpoint.
Consistent sandbox semantics: All resources support the same sandbox lifecycle (create, read, write, checkpoint, rollback).
Pluggable resource handlers: New resource types can be added by registering custom resource types without modifying existing tools.
Unified change tracking: All resource modifications flow into the same ChangeSet model.

Resource Handler Interface

Every resource type provides a handler that implements this interface:

class ResourceHandler(Protocol):
    """Handler for a specific resource type."""
    
    def read(self, path: str, sandbox: Sandbox) -> Content:
        """Read content from the sandboxed resource."""
        ...
    
    def write(self, path: str, content: Content, sandbox: Sandbox) -> Change:
        """Write content and return the Change record."""
        ...
    
    def delete(self, path: str, sandbox: Sandbox) -> Change:
        """Delete resource and return the Change record."""
        ...
    
    def list(self, pattern: str, sandbox: Sandbox) -> list[str]:
        """List paths matching pattern."""
        ...
    
    def diff(self, path: str, sandbox: Sandbox) -> str:
        """Generate diff between sandbox and original state."""
        ...
    
    def supports_operation(self, operation: OperationType) -> bool:
        """Check if this resource supports the given operation."""
        ...
    
    def discover_children(self, resource: ResourceRecord) -> list[ResourceRecord]:
        """Auto-discover child resources (called at registration and refresh)."""
        ...
    
    def content_hash(self, path: str, sandbox: Sandbox) -> str:
        """Compute content hash for identity tracking."""
        ...
    
    def create_sandbox(self, resource: ResourceRecord) -> Sandbox:
        """Create a sandbox for this resource using its type's strategy."""
        ...
    
    def create_checkpoint(self, sandbox: Sandbox) -> Checkpoint:
        """Create a checkpoint within the sandbox."""
        ...
    
    def rollback_to(self, sandbox: Sandbox, checkpoint: Checkpoint) -> None:
        """Roll back sandbox state to a checkpoint."""
        ...

Built-in Resource Handlers

Resource Type	Handler	Read	Write	Delete	Sandbox Strategy
`git-checkout`	`GitCheckoutHandler`	✓	✓	✓	`git_worktree`
`git`	`GitHandler`	✓	✗	✗	`none`
`git-commit`, `git-tree`, `git-tree-entry`	`GitObjectHandler`	✓	✗	✗	(inherits)
`git-branch`, `git-tag`, `git-stash`	`GitRefHandler`	✓	✓	✓	(inherits)
`git-remote`, `git-submodule`	`GitConfigHandler`	✓	✗	✗	(inherits)
`fs-mount`	`FilesystemHandler`	✓	✓	✓	`copy_on_write`
`fs-directory`	`FilesystemHandler`	✓	✓	✓	`copy_on_write`
`fs-file`, `fs-symlink`, `fs-hardlink`	`FilesystemHandler`	✓	✓	✓	(inherits)

Additional handlers are provided by custom resource types when they are registered.

Resource Path Resolution

Paths in tool invocations are resolved through a resource routing system that uses tool-resource bindings to determine the target resource:

sequenceDiagram
    participant Tool as Tool Invocation
    participant Router as Resource Router
    participant Handler as GitCheckoutHandler

    Tool->>Router: edit_file(path='src/main.py', ...)
    Router->>Router: Check tool's resource bindings
    Note right of Router: slot 'repo' bound to<br/>local/api-repo (git-checkout)
    Router->>Router: Resolve path within bound resource
    Note right of Router: local/api-repo:worktree:src/main.py
    Router->>Handler: Route to resource handler
    Handler->>Handler: Resolve path to sandbox worktree
    Handler->>Handler: Operate on sandboxed state
    Handler-->>Tool: Return Change record

When a tool has multiple resource slots bound, the path scheme or slot name disambiguates:

# Explicit slot reference
path://repo/src/main.py      → routes to the "repo" slot's bound resource
path://docs/api/readme.md    → routes to the "docs" slot's bound resource

# Default: unqualified paths route to the tool's primary resource slot
src/main.py                  → routes to the first (or only) resource slot

Code Intelligence & Context Discovery

Overview

CleverAgents employs a sophisticated multi-layered indexing and discovery system that enables agents to efficiently navigate and understand codebases of any scale. This system goes far beyond simple text search, providing semantic understanding of code structure, dependencies, and relationships through a combination of indexed embeddings, vector search, and an RDF-based graph store.

Critical Design Decision: All indexing happens immediately when resources are added to projects or when code changes. There is no "on-demand" indexing during agent execution. This ensures that agents always have instant access to search capabilities without any indexing delays. The computational cost is paid once upfront, not repeatedly during agent operations.

Key Design Principles:

Pluggable Architecture: Every component can be extended or replaced
Progressive Enhancement: System works with basic text search, enhances with advanced features
Eager Indexing: Indices are built immediately when resources are added and kept continuously up-to-date
Agent Awareness: Agents understand available indices through skills
Real-time Synchronization: Indices update immediately as code changes

Architecture Components

The indexing engine operates across three complementary modalities:

IndexingEngine:
  modalities:
    # Traditional text-based indexing
    text_index:
      type: "full_text_search"
      backend: "tantivy" | "elasticsearch" | "sqlite_fts"
      features:
        - Token-based search
        - Regex patterns
        - Language-aware tokenization
        - File path indexing
    
    # Semantic understanding via embeddings
    vector_index:
      type: "embedding_search"
      backend: "faiss" | "qdrant" | "weaviate" | "pgvector"
      models:
        - code: "codegen-6B-multi"
        - docs: "instructor-xl"
        - cross-modal: "clip-code"
      features:
        - Function-level embeddings
        - Class-level embeddings
        - Module-level embeddings
        - Documentation embeddings
        - Cross-language similarity
    
    # Structural understanding via graph
    graph_index:
      type: "rdf_knowledge_graph"
      backend: "blazegraph" | "stardog" | "apache_jena" | "neo4j"
      ontology: "CodeOntology"
      features:
        - AST-based relationships
        - Dependency graphs
        - Call graphs
        - Inheritance hierarchies
        - Data flow analysis

2. RDF-Based Code Knowledge Graph

The graph store represents code as a rich semantic network using RDF (Resource Description Framework) triples. This enables sophisticated queries about code structure and relationships.

Core Ontology Design:

# CodeOntology - Core vocabulary for code representation
@prefix code: <https://cleveragents.ai/ontology/code#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .

# Core Classes
code:Module a rdfs:Class ;
    rdfs:comment "A code module (file, package, namespace)" .

code:Class a rdfs:Class ;
    rdfs:comment "A class or similar construct" .

code:Function a rdfs:Class ;
    rdfs:comment "A function, method, or procedure" .

code:Variable a rdfs:Class ;
    rdfs:comment "A variable, constant, or field" .

code:Type a rdfs:Class ;
    rdfs:comment "A type definition" .

# Core Properties
code:contains a rdf:Property ;
    rdfs:domain code:Module ;
    rdfs:range code:Entity ;
    rdfs:comment "Module contains entity" .

code:imports a rdf:Property ;
    rdfs:domain code:Module ;
    rdfs:range code:Module ;
    rdfs:comment "Module imports another module" .

code:extends a rdf:Property ;
    rdfs:domain code:Class ;
    rdfs:range code:Class ;
    rdfs:comment "Class inheritance relationship" .

code:calls a rdf:Property ;
    rdfs:domain code:Function ;
    rdfs:range code:Function ;
    rdfs:comment "Function calls another function" .

code:references a rdf:Property ;
    rdfs:domain code:Entity ;
    rdfs:range code:Entity ;
    rdfs:comment "Entity references another entity" .

code:hasParameter a rdf:Property ;
    rdfs:domain code:Function ;
    rdfs:range code:Parameter ;
    rdfs:comment "Function has parameter" .

code:returns a rdf:Property ;
    rdfs:domain code:Function ;
    rdfs:range code:Type ;
    rdfs:comment "Function return type" .

# Annotations
code:hasDocstring a rdf:Property ;
    rdfs:domain code:Entity ;
    rdfs:range xsd:string .

code:hasComplexity a rdf:Property ;
    rdfs:domain code:Function ;
    rdfs:range xsd:integer ;
    rdfs:comment "Cyclomatic complexity" .

code:hasTestCoverage a rdf:Property ;
    rdfs:domain code:Entity ;
    rdfs:range xsd:decimal ;
    rdfs:comment "Test coverage percentage" .

Example Knowledge Graph Fragment:

# Concrete example: Authentication module
<file:///src/auth/auth_manager.py> a code:Module ;
    code:imports <file:///src/core/user.py> ;
    code:imports <file:///src/utils/crypto.py> ;
    code:contains <class://AuthManager> .

<class://AuthManager> a code:Class ;
    code:hasMethod <method://AuthManager.authenticate> ;
    code:hasMethod <method://AuthManager.validate_token> ;
    code:extends <class://BaseManager> ;
    code:hasDocstring "Manages user authentication and session tokens" .

<method://AuthManager.authenticate> a code:Function ;
    code:hasParameter <param://username> ;
    code:hasParameter <param://password> ;
    code:returns <type://AuthToken> ;
    code:calls <method://CryptoUtils.hash_password> ;
    code:calls <method://UserDB.find_user> ;
    code:hasComplexity 8 ;
    code:hasTestCoverage 0.95 .

Advanced Graph Queries:

# Find all functions that manipulate user authentication
PREFIX code: <https://cleveragents.ai/ontology/code#>
SELECT ?function ?module
WHERE {
    ?function a code:Function ;
              code:calls*/code:references ?entity .
    ?entity rdfs:label ?label .
    FILTER(CONTAINS(LCASE(?label), "auth") || CONTAINS(LCASE(?label), "user"))
    ?module code:contains ?function .
}

# Find circular dependencies
SELECT ?module1 ?module2
WHERE {
    ?module1 code:imports+ ?module2 .
    ?module2 code:imports+ ?module1 .
    FILTER(?module1 != ?module2)
}

# Find most complex untested functions
SELECT ?function ?complexity
WHERE {
    ?function a code:Function ;
              code:hasComplexity ?complexity ;
              code:hasTestCoverage ?coverage .
    FILTER(?complexity > 10 && ?coverage < 0.5)
}
ORDER BY DESC(?complexity)
LIMIT 10

3. Intelligent Context Assembly Pipeline

The context assembly pipeline leverages all three indices to build optimal context for each agent:

class ContextAssemblyPipeline:
    def assemble_context(self, 
                        query: str, 
                        actor_type: str,
                        resource_scope: List[Resource],
                        max_tokens: int) -> Context:
        
        # Stage 1: Query Understanding
        intent = self.analyze_query_intent(query)
        entities = self.extract_entities(query)  # Classes, functions, concepts
        
        # Stage 2: Multi-Modal Search
        results = SearchResults()
        
        # Text search for exact matches
        if intent.needs_exact_match:
            text_results = self.text_index.search(
                query=query,
                filters={"resources": resource_scope},
                limit=100
            )
            results.add(text_results)
        
        # Vector search for semantic similarity
        if intent.needs_semantic_match:
            query_embedding = self.embed_query(query, actor_type)
            vector_results = self.vector_index.search(
                embedding=query_embedding,
                filters={"resources": resource_scope},
                limit=50
            )
            results.add(vector_results)
        
        # Graph traversal for structural relationships
        if entities:
            graph_results = self.graph_index.traverse(
                start_nodes=entities,
                patterns=self.get_patterns_for_actor(actor_type),
                max_depth=3,
                limit=50
            )
            results.add(graph_results)
        
        # Stage 3: Relevance Ranking
        ranked_results = self.rank_by_relevance(
            results=results,
            actor_type=actor_type,
            query_intent=intent
        )
        
        # Stage 4: Context Optimization
        context = self.optimize_context(
            ranked_results=ranked_results,
            max_tokens=max_tokens,
            strategy=self.get_strategy_for_actor(actor_type)
        )
        
        return context
    
    def get_patterns_for_actor(self, actor_type: str) -> List[GraphPattern]:
        """Different actors need different traversal patterns"""
        patterns = {
            "strategist": [
                "module_dependencies",      # Understand architecture
                "interface_boundaries",     # Find API surfaces
                "test_coverage_gaps"        # Identify risks
            ],
            "executor": [
                "implementation_details",   # Get full function bodies
                "local_dependencies",       # Find what to change
                "usage_patterns"           # Understand call sites
            ],
            "reviewer": [
                "change_impact_analysis",   # What could break
                "similar_patterns",        # Consistency checks
                "test_relationships"       # Verification paths
            ]
        }
        return patterns.get(actor_type, ["general_traversal"])

4. Plugin Architecture for Extensibility

The system is designed for extensibility at every level:

PluginSystem:
  # Language-specific analyzers
  analyzers:
    python:
      class: "PythonAnalyzer"
      features:
        - AST parsing via ast module
        - Type inference via mypy
        - Import resolution
        - Docstring extraction
    
    typescript:
      class: "TypeScriptAnalyzer"
      features:
        - TSC-based parsing
        - Type extraction
        - Module resolution
        - JSDoc parsing
    
    rust:
      class: "RustAnalyzer"
      features:
        - rust-analyzer integration
        - Lifetime analysis
        - Trait resolution
        - Macro expansion
    
    # Custom analyzer example
    custom_dsl:
      class: "CustomDSLAnalyzer"
      config:
        grammar: "path/to/grammar.peg"
        semantic_rules: "path/to/rules.yaml"
  
  # Index backend providers
  backends:
    graph:
      - name: "blazegraph"
        class: "BlazegraphBackend"
        scalability: "billions of triples"
        features: ["SPARQL", "reasoning", "geospatial"]
      
      - name: "neo4j"
        class: "Neo4jBackend"
        scalability: "enterprise"
        features: ["Cypher", "APOC", "GDS"]
      
      - name: "custom_graph"
        class: "MyCustomGraphDB"
        config:
          connection: "custom://localhost:7687"
    
    vector:
      - name: "faiss"
        class: "FaissBackend"
        scalability: "100M vectors"
        features: ["GPU acceleration", "HNSW"]
      
      - name: "qdrant"
        class: "QdrantBackend"
        scalability: "distributed"
        features: ["filtering", "payloads", "snapshots"]
  
  # Embedding model providers
  embedders:
    - name: "openai"
      class: "OpenAIEmbedder"
      models: ["text-embedding-3-large", "text-embedding-3-small"]
    
    - name: "local"
      class: "LocalEmbedder"
      models: ["all-MiniLM-L6-v2", "instructor-xl"]
    
    - name: "custom"
      class: "MyFineTunedEmbedder"
      model_path: "path/to/model"

5. Agent Skills for Code Intelligence

Agents interact with the code intelligence system through a specialized skill (local/code-intelligence) that contains tools for semantic search, dependency analysis, and refactoring:

# Actor references the code intelligence skill
actors:
  code_explorer:
    type: llm
    config:
      actor: anthropic/claude-3-opus
    skills:
      - local/code-intelligence   # Provides search_code_semantically,
                                  # analyze_dependencies, suggest_refactoring_targets

The local/code-intelligence skill uses anonymous inline tools to wrap the code intelligence subsystem. These tools are defined inline because they are tightly coupled to the skill's specific implementation and not reused elsewhere (if any were needed in multiple contexts, they would be registered independently via agents tool add and referenced by name):

# File: skills/code-intelligence.yaml
skill:
  name: local/code-intelligence
  description: "Semantic code search, dependency analysis, and refactoring recommendations"

  anonymous_tools:
    - name: search_code_semantically
      description: "Find code similar to a concept using vector search, enriched with dependency context"
      input_schema:
        type: object
        properties:
          query: { type: string }
          scope: { type: string, default: "all" }
          limit: { type: integer, default: 10 }
        required: [query]
      capability:
        read_only: true
      code: |
        results = ctx.code_intelligence.vector_search(
            query=params["query"],
            scope=params.get("scope", "all"),
            limit=params.get("limit", 10)
        )
        for result in results:
            result.context = ctx.code_intelligence.get_dependencies(
                entity=result.entity_id, depth=2
            )
        return results

    - name: analyze_dependencies
      description: "Analyze module dependencies using graph store"
      input_schema:
        type: object
        properties:
          module_path: { type: string }
        required: [module_path]
      capability:
        read_only: true
      code: |
        module = params["module_path"]
        deps = ctx.code_intelligence.graph_query(f'''
            PREFIX code: <https://cleveragents.ai/ontology/code#>
            SELECT ?dep ?type WHERE {{
                <{module}> code:imports* ?dep . ?dep a ?type .
            }}
        ''')
        return {
            "direct_deps": len([d for d in deps if d.distance == 1]),
            "transitive_deps": len(deps),
            "circular_deps": ctx.code_intelligence.find_circular_deps(module),
            "dependency_graph": deps
        }

    - name: suggest_refactoring_targets
      description: "Combine text, graph, and vector search to find refactoring targets"
      input_schema:
        type: object
        properties:
          scope: { type: string }
        required: [scope]
      capability:
        read_only: true
      code: |
        todos = ctx.code_intelligence.text_search(
            pattern="(TODO|FIXME|HACK):", scope=params["scope"]
        )
        complex_functions = ctx.code_intelligence.graph_query('''
            SELECT ?func ?complexity ?coverage WHERE {
                ?func a code:Function ;
                      code:hasComplexity ?complexity ;
                      code:hasTestCoverage ?coverage .
                FILTER(?complexity > 15 || ?coverage < 0.3)
            } ORDER BY DESC(?complexity)
        ''')
        smells = []
        for pattern in ["duplicate code", "long method", "large class"]:
            smells.extend(ctx.code_intelligence.find_similar_code(
                pattern=pattern, threshold=0.8
            ))
        return {
            "high_priority": complex_functions[:5],
            "technical_debt": todos,
            "code_smells": smells,
            "suggested_order": ctx.code_intelligence.rank_by_impact(
                complex_functions + todos + smells
            )
        }

6. Real-time Index Synchronization

The system maintains index freshness through immediate, proactive updates:

class IndexSynchronizer:
    def __init__(self):
        self.file_watcher = FileSystemWatcher()
        self.git_monitor = GitChangeMonitor()
        self.incremental_indexer = IncrementalIndexer()
    
    def on_resource_added(self, resource: Resource, project: Project):
        """When a resource is added to a project, index it immediately"""
        # Full initial indexing - happens once when resource is added
        with self.progress_reporter(f"Indexing {resource.name}") as progress:
            files = self.scan_resource(resource)
            total = len(files)
            
            # Parallel indexing for performance
            with ThreadPoolExecutor(max_workers=cpu_count()) as executor:
                futures = []
                
                for i, file in enumerate(files):
                    future = executor.submit(self.index_file_complete, file)
                    futures.append(future)
                    progress.update(i / total)
                
                # Wait for all indexing to complete
                for future in futures:
                    future.result()
        
        # Now set up watchers for incremental updates
        self.setup_watchers(resource)
        
        # Mark resource as indexed and ready
        resource.indexing_status = "ready"
        self.notify_agents_index_ready(resource)
        
        # CRITICAL: Agents can now immediately search this resource
        # No "warming up" period - indices are complete and ready
    
    def index_file_complete(self, file_path: str):
        """Comprehensive initial indexing of a file"""
        # Parse file once
        ast = self.parse_file(file_path)
        
        # Update all indices immediately
        self.update_text_index(file_path, ast)
        self.update_vector_embeddings(file_path, ast)
        self.update_graph_triples(file_path, ast)
        
        # Extract and index all metadata
        self.index_symbols(file_path, ast)
        self.index_dependencies(file_path, ast)
        self.index_complexity_metrics(file_path, ast)
    
    def setup_watchers(self, project: Project):
        # File system watching for immediate updates
        self.file_watcher.watch(
            path=project.root_path,
            events=["create", "modify", "delete"],
            callback=self.on_file_change
        )
        
        # Git monitoring for batch updates (using linked git resource)
        git_resource = project.get_linked_resource(type="git-checkout")
        self.git_monitor.watch(
            repo=git_resource,
            events=["commit", "merge", "rebase"],
            callback=self.on_git_change
        )
    
    def on_file_change(self, event: FileEvent):
        # Quick incremental update
        if event.type in ["create", "modify"]:
            # Parse changed file
            ast = self.parse_file(event.path)
            
            # Update indices
            self.update_text_index(event.path, ast)
            self.update_vector_embeddings(event.path, ast)
            self.update_graph_triples(event.path, ast)
        
        elif event.type == "delete":
            self.remove_from_indices(event.path)
    
    def on_git_change(self, event: GitEvent):
        # Batch update for git operations
        changed_files = event.get_changed_files()
        
        # Optimize batch processing
        with self.batch_updater() as updater:
            for file in changed_files:
                updater.queue_update(file)
            
            # Process in parallel
            updater.execute(parallel=True)
    
    def update_graph_triples(self, file_path: str, ast: AST):
        # Generate RDF triples from AST
        triples = []
        
        # Module-level triples
        module_uri = self.uri_for_file(file_path)
        for import_stmt in ast.imports:
            imported_uri = self.resolve_import(import_stmt)
            triples.append((module_uri, "code:imports", imported_uri))
        
        # Function-level triples
        for func in ast.functions:
            func_uri = self.uri_for_function(func)
            triples.append((module_uri, "code:contains", func_uri))
            triples.append((func_uri, "a", "code:Function"))
            triples.append((func_uri, "code:hasComplexity", func.complexity))
            
            # Call relationships
            for call in func.calls:
                called_uri = self.resolve_call(call)
                triples.append((func_uri, "code:calls", called_uri))
        
        # Update graph store
        self.graph_store.update_triples(triples)

7. Fallback to Traditional Search

When advanced features are unavailable, the system gracefully degrades:

class FallbackSearchProvider:
    def search(self, query: str, resources: List[Resource]) -> SearchResults:
        # Try advanced search first
        try:
            if self.vector_index.is_available():
                return self.vector_search(query, resources)
        except ServiceUnavailable:
            pass
        
        # Fallback to graph search
        try:
            if self.graph_index.is_available():
                return self.graph_search(query, resources)
        except ServiceUnavailable:
            pass
        
        # Ultimate fallback: grep-like text search
        return self.basic_text_search(query, resources)
    
    def basic_text_search(self, query: str, resources: List[Resource]):
        # Use ripgrep or similar for fast text search
        results = []
        
        for resource in resources:
            matches = ripgrep.search(
                pattern=query,
                path=resource.path,
                context_lines=3
            )
            
            for match in matches:
                results.append(SearchResult(
                    file=match.file,
                    line=match.line,
                    content=match.content,
                    score=1.0  # Basic scoring
                ))
        
        return results

Index Lifecycle

The system follows a clear lifecycle for index management:

Index Lifecycle:
  1_resource_added:
    trigger: "agents resource add / agents project link-resource"
    action: "Immediate full indexing"
    duration: "Depends on size (10K files ~1 minute)"
    result: "All indices ready for instant search"
    
  2_code_changed:
    trigger: "File modification detected"
    action: "Immediate incremental update"
    duration: "Milliseconds per file"
    result: "Indices stay synchronized"
    
  3_resource_removed:
    trigger: "agents project unlink-resource / agents resource remove"
    action: "Immediate index cleanup"
    duration: "Seconds"
    result: "No stale data in indices"
    
  4_maintenance:
    trigger: "Scheduled or manual"
    action: "Reindex for consistency"
    duration: "Background process"
    result: "Indices optimized and verified"

Key Guarantees:
  - "No search happens on stale data"
  - "No 'index building' delays during agent execution"
  - "Changes visible in search immediately"
  - "Initial indexing is a one-time cost per resource"

Integration with Context Tiers

The Code Intelligence system directly feeds into the three-tier context architecture:

Context Tier Integration:
  hot_tier:
    source: "Real-time results from code intelligence"
    content:
      - Currently edited files
      - Direct dependencies
      - Immediately relevant functions
    
  warm_tier:
    source: "Indexed embeddings and graph queries"
    content:
      - Recent search results
      - Cached graph traversals
      - Vector similarity matches
      - Active decision contexts
    
  cold_tier:
    source: "Historical indices and compressed data"
    content:
      - Previous plan analyses
      - Archived dependency graphs
      - Historical refactoring patterns
      - Learned codebase conventions

Performance Characteristics

The system maintains pre-computed indices for instant search performance:

Performance Metrics:
  initial_indexing_speed:
    text_index: "10,000 files/minute"
    vector_index: "1,000 files/minute (with GPU)"
    graph_index: "5,000 files/minute"
  
  query_performance:
    text_search: "< 100ms for 1M files"
    vector_search: "< 200ms for 10M embeddings"
    graph_traversal: "< 500ms for 3-hop queries"
    
  storage_requirements:
    text_index: "~10% of source size"
    vector_index: "~1GB per 100K functions"
    graph_store: "~100MB per 10K files"
    
  scalability:
    max_files: "No hard limit (tested to 10M files)"
    max_graph_size: "1B+ triples"
    max_vectors: "100M+ embeddings"

Progressive Enhancement Path

Organizations can adopt Code Intelligence features progressively. At each stage, existing resources are reindexed to take advantage of new capabilities:

adoption_stages:
  stage_1_basic:
    features: ["text search", "file watching"]
    requirements: ["ripgrep", "sqlite"]
    initial_setup: "Index all text content on resource add"
    benefit: "Instant exact-match search"
    
  stage_2_semantic:
    features: ["vector embeddings", "similarity search"]
    requirements: ["embedding model", "vector DB"]
    initial_setup: "Generate embeddings for all code (one-time cost)"
    benefit: "Instant semantic similarity search"
    
  stage_3_structural:
    features: ["RDF graph", "relationship queries"]
    requirements: ["graph database", "language analyzers"]
    initial_setup: "Parse and build complete knowledge graph"
    benefit: "Instant relationship queries"
    
  stage_4_intelligent:
    features: ["ML-driven ranking", "automated analysis"]
    requirements: ["GPU", "training data"]
    initial_setup: "Pre-compute ML features and rankings"
    benefit: "Instant intelligent suggestions"
    
  stage_5_custom:
    features: ["Domain-specific ontologies", "Custom analyzers"]
    requirements: ["Domain expertise", "Custom development"]
    initial_setup: "Build domain-specific indices"
    benefit: "Instant domain-aware intelligence"

This Code Intelligence & Context Discovery system ensures that CleverAgents can efficiently work with codebases of any size, providing agents with the contextual understanding they need to make intelligent decisions about code changes, refactoring, and feature development.

Summary of Timing:

Indexing: Eager (happens immediately when resources are added/changed)
Searching: Instant (because indices are pre-computed and ready)
Sandboxing: Lazy (only when execution needs to modify a resource)
Context Assembly: Real-time (but fast because it queries ready indices)

This design ensures agents never wait for index building during execution, providing a responsive and predictable experience even on massive codebases.

Context

Note: This section describes the high-level context management system. For details on how context is discovered and indexed, see the Code Intelligence & Context Discovery section above.

Context in CleverAgents is not "dump all files into an LLM." It is a system that:

finds relevant information from resources,
injects appropriate subsets into each actor/node,
and scales to large repositories.

Current Reality and Planned Improvements

key concepts:

There is a global context concept,
But nodes only see what is injected into their prompts,
It's functional but not yet elegant,
A more advanced automated system is planned.

Tiered Context Architecture (Hot/Warm/Cold)

The system uses a sophisticated three-tier memory architecture that enables working with massive codebases without holding everything in memory:

Hot context (hot cache) The small set of immediately relevant chunks injected into the current actor prompt. When working on a 50,000 file codebase, hot context focuses on the immediate task (e.g., 10-20 files for a specific refactoring).
Warm context Recent decisions and their contexts from this plan tree - quickly accessible. Includes indexed embeddings, vector search results, and graph store representations. Maintains the decision chain that led to the current work.
Cold storage Historical decisions from past plans on this codebase - queryable but not in active memory. Long-term storage in SQLite or caching systems containing prior summaries, older plan artifacts, and historical patterns (e.g., "last time we refactored auth, we also had to update these services").

Promotion/demotion behavior:

System analyzes current query
Promotes relevant data upward (cold → warm → hot)
Demotes stale data out of hot to keep prompts tight
Preserves complete context snapshots for every decision

This architecture leverages the key insight that software development is inherently local - even in huge codebases, individual changes typically touch a bounded set of files. The Decision Tree captures these localities.

Actor-Specific Context Views

A key missing feature identified in the notes is per-actor context views, filtering, relevance, and actor-aware context limits.

The intended direction:

global context exists at plan level,
each actor gets a "view" of that context tuned to their role,
memory may be shared or per-plan depending on design choices.

Actor Context View Service (Proposed)

A dedicated module/service that:

maintains actor-specific "context views,"
tracks actor memory and relevance,
enforces actor-specific limits (tokens, file types, etc.).

Initial Context vs Deep Context

A practical approach mentioned:

Initial context is high-level (repo tree, language, overview),
Then the system searches for relevant details iteratively via RAG.

This strongly suggests CleverAgents should define:

an "initial context recipe" per project type (codebase vs documents vs infra),
iterative context refinement loops during strategize/execute.

Behavior

Automation Levels

Automation levels determine which phase transitions happen automatically.

Automation Level Modes

Mode	Behavior
Manual	User explicitly triggers: create → use → execute → apply. Every phase transition requires a command. Every decision point pauses for human input. User sees context, alternatives, and recommendation. User provides explicit choice or custom guidance.
Review-before-apply	Strategize + Execute happen automatically. AI makes all decisions autonomously. System pauses before Apply to show diff and ask for approval. User can approve, reject, or correct specific decisions.
Full automation	System runs all phases automatically end-to-end. AI makes all decisions. Execution proceeds through apply. Human notified of completion. Rollback available if issues detected.

Progressive Trust Building

New users typically follow this progression:

Start with manual mode to understand system behavior
Move to review-before-apply as confidence builds
Enable full automation for specific task types
Gradually expand full automation scope

Semantic Escalation

Even in full automation mode, the system understands when it needs help:

class AutonomyController:
    def assess_decision_confidence(self, decision, context):
        factors = {
            'past_success_rate': self.get_historical_success(decision.type),
            'codebase_familiarity': self.get_familiarity_score(context.project),
            'risk_assessment': self.evaluate_risk(decision),
            'invariant_complexity': self.analyze_invariants(decision)
        }
        
        confidence = self.compute_confidence(factors)
        
        if confidence < self.threshold:
            if self.automation_level == 'full':
                # Even in full automation, critical decisions escalate
                return RequestHumanGuidance(decision, factors)
        
        return ProceedAutonomously(decision)

Automation Level Hierarchy

Automation levels are determined using this precedence (highest to lowest):

Plan-level: Explicitly set when using an action on projects
Session-level: Set for the current session
Global-level: Persisted application configuration

# Set global automation level (persists across sessions)
agents config set automation-level review-before-apply

# Set session automation level (overrides global for this session)
agents session set automation-level full-automation

# Use action with explicit automation level (overrides session and global)
agents plan use local/my-action --project my-proj --automation-level manual

Automation Level Persistence Rules

Global level: Persisted in application configuration. Default is manual on fresh install.
Session level: Lives for the duration of the session. Not persisted.
Plan level: Once a plan's automation level is determined (at the moment of use), it is locked to that plan. Even if the session or global level changes later, the plan retains its original automation level.
Explicit change: A plan's automation level can be changed explicitly after creation:

agents plan set-automation-level <plan_id> full-automation

Child Plan Automation Levels

Child plans inherit the parent plan's automation level.

However, if the parent plan's automation level is changed explicitly mid-execution, new child plans will use the new level while already-completed child plans retain their original level.

Granular Automation Flags

For fine-grained control, additional flags can modify behavior:

auto_strategize - Automatically proceed from Action to Strategize
auto_execute - Automatically proceed from Strategize to Execute
auto_apply - Automatically proceed from Execute to Apply
auto_retry_on_failure - Automatically retry failed phases

This allows combinations like:

Auto strategize, manual execute, manual apply (for risky infra tasks)
Auto strategize + execute, manual apply (the review-before-apply pattern)

Validation and Guardrails

Plan generation validation

The validation logic is stubbed and must be implemented. The spec should require:

validate action schema
validate actor availability
validate required skills exist
validate permission policy
validate rollback feasibility (if enabled)
validate project resource accessibility

This prevents "plan runs with fake providers" and other surprises.

Cost / rate limits

Future concerns:

API call limits
cost caps

So CleverAgents should define:

per-plan budgets
per-session budgets
per-org budgets
per-actor max tool calls / max retries

Correcting Plans (Core Feature)

Correcting plans is where CleverAgents becomes more than "a fancy prompt runner."

The Goal

When a plan makes a wrong decision early, we want to:

correct the decision,
recompute only the affected subtree,
preserve unaffected work.

This is explicitly described: "redo everything below that decision, not the entire code base."

Decision Tree Representation

Every plan records (see Decision Data Model section):

decisions (choice points) - created during Strategize, including invariant_enforced, subplan_spawn, and subplan_parallel_spawn decisions
dependencies (which later work depended on that decision)
child plans spawned because of that decision - populated during Execute
artifacts generated under that branch

This makes plan runs auditable and correctable.

Two Correction Modes

Revert-from-history correction (--mode=revert)

Find the decision point in the tree
Roll back all changes (code and non-code) to that point
Re-run from that decision point forward
Keep old execution artifacts for comparison
Potentially expensive if high up in the tree

Add-at-end correction (--mode=append)

Leave history intact
Append a new plan at the end that fixes the outcome
Cheaper and safer sometimes
Does not rewrite history

Correction Flow (Revert Mode)

When user requests correction at Decision B:

Mark for Correction

Decision B.superseded_by = new_decision_id

Identify Downstream Impact
- Recursively collect all decisions that depend on Decision B (including invariant_enforced, subplan_spawn, and subplan_parallel_spawn decisions)
- Collect all child plans spawned from those decisions
- These form the "affected subtree"
Rollback Resources
- For each affected decision's artifacts_produced:
  - Rollback to the checkpoint before that artifact was created
- For affected child plans:
  - Rollback their sandboxes entirely
Preserve for Comparison
- Archive the original subtree's artifacts
- Create a CorrectionAttempt record linking old and new
Re-execute from Decision Point
- Restore context to Decision B.context_snapshot
- User provides new guidance/correction
- Re-run execution from that point
- New decisions get is_correction: true, corrects_decision_id: B
Apply as Normal
- The corrected plan goes through normal Apply gating
- Diff shows changes from the correction

History Cleanup

History can only be flagged for cleanup after a plan is Applied.

Once a plan is applied:

It can no longer be rolled back
Old correction artifacts can be archived or deleted based on retention policy
The decision tree is preserved for audit purposes

CLI Commands for Correction

# View decision tree
agents plan tree <plan_id>
agents plan tree <plan_id> --format=json  # For visualization tools

# Inspect a specific decision
agents plan explain <decision_id>
# Shows: question, chosen option, alternatives, rationale, downstream impact

# Correct via revert-and-replay
agents plan correct <decision_id> --mode=revert --guidance "<what the decision should be>"
# Re-executes from that point with the new guidance

# Correct via append (add fix at end)  
agents plan correct <decision_id> --mode=append --guidance "<description of the fix>"
# Creates a new child plan to fix the outcome without rewriting history

# Compare old vs new after correction
agents plan diff <correction_attempt_id>

Correction Safety

Corrections always:

Create a new attempt revision (increment plan.attempt)
Preserve old artifacts for diff/compare
Run execute in sandbox again
Require apply gating again
Never modify already-applied changes

This keeps history reproducible and prevents accidental destructive edits.

Human-in-the-Loop Collaboration

Even though the direction is "more autonomous," the transcript explicitly recognizes that real workflows require engineers to collaborate with the system, editing code while it works, and using better UX integration (TUI/web/IDE).

So CleverAgents should aim for:

visibility: what is it doing now?
interruptibility: pause/cancel/retry
editability: allow user to modify strategy before execute
reconciliation: detect if user changed sandbox files mid-run and handle it

UI / Interaction Model

CLI-first + TUI + Web App + IDE

The system intends to be CLI-first, with:

a TUI built using Textual,
which can generate a web app "for free,"
and later an IDE plugin that embeds the TUI in the IDE.

This implies a "single UI codebase" model:

same underlying view logic,
multiple frontends.

Plan Tree Visualization

The TUI should show:

plan list
plan details
plan tree (ASCII)
diff view
approvals

And should later allow exporting the tree as image (PNG) or JSON for other visualization tools.

Additional Recommended Sections (Missing from Draft but Important)

Storage and Persistence

CleverAgents should define where each concept lives:

Actions: stored in a registry (local files or server DB)
Actors: stored similarly (config files + DB indexing)
Projects: stored locally or on server
Plans: stored in plan DB with full logs
Context indexes: vector store / graph store / SQLite
Artifacts: filesystem or object storage

Observability

To debug large plans:

every phase should emit events
every actor call should log prompt/context references
every tool call should log resource access (with parent skill noted)
every checkpoint should be recorded

Security Model

sandbox isolation
resource-level ACLs
prompt injection mitigations (server mode)
secret management (API keys, DB credentials)
audit logs for apply

Extensibility

plugin system for skills
custom node types
action templates
actor templates (noted as missing currently)

Summary of Key Intended Behaviors (If You Only Read One Section)

Plans follow Action → Strategize → Execute → Apply with automation levels controlling transitions.
Strategize is read-only and produces a strategy + blueprint.
Execute happens in a sandbox, can spawn child plans, and should support checkpoints/rollback when enabled.
Apply commits changes from sandbox to real project after review/validation.
Actors are hierarchical: an actor can be a single agent or an entire graph.
Graph nodes can be actors or tools (tools are provided by referenced skills, which aggregate tools from MCP servers, Agent Skills folders, built-ins, and custom code).
Context should evolve toward hot/warm/cold tiers and actor-specific context views.
The system is designed for large tasks where the user can correct a decision and only recompute downstream work, visualizable as a plan decision tree.

The system can handle Firefox-scale projects not through magic, but through:

Hierarchical decomposition breaking massive tasks into bounded work
Persistent decision graphs maintaining context across any scale
Isolated execution preventing cascading failures
Semantic validation catching errors before propagation
Progressive automation building trust through incremental success

Future details to add to this document:

a canonical JSON/YAML schema for Actions, Actors, Projects, Plans, Skills, and Context Views,
a CLI command reference (every command, flags, examples),
and a set of end-to-end example workflows (single project, multi-project, infra task, paper-writing task) consistent with this spec.

Work Remaining to Make CleverAgents Fully Functional

This section describes what remains to be done to bring the current CleverAgents codebase up to the specification.

Last Updated: February 6, 2026

Current State Assessment

What's Implemented

Based on analysis of the current codebase:

Plan Lifecycle Foundation - The 4-phase lifecycle (Action → Strategize → Execute → Apply) is partially implemented in plan_lifecycle_service.py
Database Models - Models exist for projects, plans, contexts, changes, and actors
LangGraph Integration - Graph-based workflow support exists but is not fully connected to the plan workflow
Reactive System - A reactive system with stream routing is present
Actor System - Actor models and services exist but lack full behavioral definitions
Basic Context Analysis - Simple context loading and analysis capabilities
Change Tracking - Basic Change and ChangeSet models exist

What's Missing

Critical gaps between the specification and current implementation:

No Resource Abstraction - The unified resource layer for files, databases, APIs is entirely missing
No Sandboxing - Execute phase writes directly to files without isolation
No Decision Tree - No decision tracking, storage, or correction mechanism
No Skills/MCP Integration - No skill registry, skill YAML parsing, tool adapters, or MCP protocol support
Single-File Limitation - Hard-coded to generate exactly one file per plan
Text-Based Code Generation - Still parsing LLM output instead of tool-based approach
No Checkpointing - No rollback or checkpoint capabilities
No Code Intelligence - Missing indexing, vector search, and RDF graph store
No Context Tiers - No hot/warm/cold memory architecture
Limited Validation - Basic stub validation instead of semantic checks

Work Items by Priority

1) Implement Tool-Based Resource Modification (Critical Foundation)

Problem

The current system generates code as a single text blob that gets written to one file. The specification requires a modern tool-based approach where LLMs invoke discrete operations on resources.

Implementation Steps

Create Resource Abstraction Layer

# New modules needed:
src/cleveragents/domain/models/resources.py
src/cleveragents/domain/resources/handlers.py
src/cleveragents/domain/resources/sandbox.py

Implement Built-in Tools (via built-in skills)

# Core file operations (provided by built-in skill groups)
read_file(path: str) -> str
write_file(path: str, content: str) -> None
edit_file(path: str, changes: list[Edit]) -> None
delete_file(path: str) -> None
move_file(src: str, dst: str) -> None
create_directory(path: str) -> None
list_files(pattern: str) -> list[str]
search_files(pattern: str, content_pattern: str) -> list[Match]

Connect Tools to ChangeSet
- Each tool invocation that modifies resources creates a Change record
- ChangeSet accumulates these changes during execution
- No more parsing LLM text output for code

Estimated Effort: 2-3 weeks

2) Implement Sandbox Infrastructure (Critical for Safety)

Problem

Execute phase currently writes directly to the project. The specification requires all changes happen in an isolated sandbox that can be reviewed before applying.

Implementation Steps

Define Sandbox Interface

class Sandbox(Protocol):
    def create() -> SandboxRef
    def read(path: str) -> Content
    def write(path: str, content: Content) -> Change
    def diff() -> DiffView
    def commit() -> None
    def rollback() -> None

Implement Sandbox Strategies
- GitWorktreeSandbox - For git repositories (preferred)
- FilesystemCopySandbox - For non-git projects
- TransactionSandbox - For databases
- NoOpSandbox - For non-sandboxable resources
Lazy Sandbox Creation
- Only create sandboxes when resources are accessed
- Each plan gets its own sandbox namespace

Estimated Effort: 2 weeks

3) Build Decision Tree System (Core Innovation)

Problem

No decision tracking exists. The specification's key innovation is recording every decision with full context, enabling correction without full re-execution.

Implementation Steps

Create Decision Models

-- New tables needed
CREATE TABLE decisions (
    decision_id TEXT PRIMARY KEY,  -- ULID
    plan_id TEXT NOT NULL,
    parent_decision_id TEXT,
    decision_type TEXT NOT NULL,
    question TEXT NOT NULL,
    chosen_option TEXT NOT NULL,
    alternatives_considered TEXT,  -- JSON array
    context_snapshot TEXT NOT NULL,  -- JSON
    created_at TEXT NOT NULL
);

Implement Decision Recording
- Every choice during Strategize creates a Decision record
- Capture complete context snapshot with each decision
- Track downstream dependencies
Build Correction Mechanism
```
agents plan correct <decision_id> --mode=revert --guidance "<new decision>"
```
- Mark decision as superseded
- Recompute only affected subtree
- Preserve unaffected work

Estimated Effort: 3 weeks

4) Implement Code Intelligence System (Scalability Enabler)

Problem

Current context is limited to a few hundred characters from a few files. Large codebases require intelligent context discovery.

Implementation Steps

Eager Indexing on Resource Add

def on_resource_added(resource: Resource):
    # Index immediately when resource added to project
    index_text_content(resource)      # Full-text search
    generate_embeddings(resource)     # Vector embeddings
    build_knowledge_graph(resource)   # RDF triples

Three-Index Architecture
- Text Index: Tantivy/SQLite FTS for exact matches
- Vector Index: FAISS/Qdrant for semantic search
- Graph Store: RDF store for relationships
Tiered Context System
- Hot: Current working set (in LLM context)
- Warm: Recent decisions and search results
- Cold: Historical data and patterns

Estimated Effort: 4 weeks

5) Complete Actor System with Behavioral Definitions

Problem

Actors exist but don't define behavior beyond model selection. The specification requires actors to be composable graphs with tools, memory, and context policies.

Implementation Steps

Extend Actor Configuration

actors:
  my_strategist:
    type: graph
    config:
      provider: anthropic
      model: claude-3-opus
      memory_policy: per_plan
      context_view: architect  # High-level view
    skills:
      - local/file-ops             # provides read_file
      - local/code-intelligence    # provides search_code, analyze_dependencies
    routes:
      strategize:
        entry_point: analyze
        nodes:
          - name: analyze
            type: llm
          - name: plan
            type: llm

Implement Tool Access Policies
- Strategy actors: read-only tools
- Execute actors: read/write within sandbox
- Apply actors: commit tools
Actor-Specific Context Views
- Strategist: Architecture, dependencies, patterns
- Executor: Implementation details, specific files
- Reviewer: Diffs, tests, risk analysis

Estimated Effort: 2 weeks

6) Resource System, Resource Types, and Resource Registry

Problem

Resources are currently defined inline within projects. The specification requires resources to be independently registered first-class entities with a type system, DAG relationships (physical/virtual), auto-discovery, and content-identity tracking. Tools need resource bindings to declare and resolve their resource dependencies.

Implementation Steps

Resource Type Registry and CLI
- Implement 24 built-in resource types: 15 physical (git-checkout, git, git-remote, git-branch, git-tag, git-commit, git-tree, git-tree-entry, git-stash, git-submodule, fs-mount, fs-directory, fs-file, fs-symlink, fs-hardlink) and 9 virtual (file, directory, symlink, commit, branch, tag, remote, submodule, tree)
- Implement resource type YAML parsing and validation for custom types
- Implement agents resource type add [--upgrade]/remove/list/show commands
- Implement dynamic CLI subcommand registration (custom types create new agents resource add subcommands)
Resource Registry and CLI
- Implement agents resource add <type>/remove/list/show/tree commands
- Implement Resource Registry persistence in database
- Implement DAG parent/child relationships with type constraints and cycle detection
- Implement agents resource link-child/unlink-child for manual DAG management
Auto-Discovery System
- Implement handler-driven child resource discovery (git-checkout discovers git + fs-directory worktree root; git discovers remotes, branches, tags, commits, stashes, submodules; git-commit discovers root git-tree; git-tree discovers tree entries + subtrees; fs-mount discovers root fs-directory; fs-directory discovers subdirectories, files, symlinks, hardlinks)
- Implement resource reuse during discovery (link existing resources instead of duplicating)
- Implement refresh mechanism for keeping discovered children up to date
Physical/Virtual Resource Model
- Implement content hashing for identity tracking
- Implement virtual resource linking (shared virtual parents for identical physical resources)
- Implement divergence detection (unlink when content changes)
Project-Resource Linking
- Replace agents project add-resource/remove-resource with link-resource/unlink-resource
- Implement project-level overrides (read-only, alias)
- Migrate any existing inline resource data to Resource Registry
Resource Handlers
- Implement GitCheckoutHandler with auto-discovery, sandbox creation, checkpoint support
- Implement GitHandler for git repository structure discovery (remotes, branches, tags, commits, stashes, submodules)
- Implement GitObjectHandler for git-commit, git-tree, git-tree-entry (read-only access to git objects)
- Implement GitRefHandler for git-branch, git-tag, git-stash (read/write ref manipulation)
- Implement GitConfigHandler for git-remote, git-submodule (read-only config access)
- Implement FilesystemHandler with auto-discovery for fs-mount, fs-directory, fs-file, fs-symlink, fs-hardlink
- Implement handler plugin system for custom resource types

Estimated Effort: 5 weeks

7) MCP Integration, Tool System, Skill System, and Tool-Resource Bindings

Problem

No tool or skill abstraction exists. The specification defines tools as independently registered operations managed via agents tool CLI commands, and skills as namespaced collections of tools managed via agents skill CLI commands. Tools can be sourced from MCP servers, Agent Skills folders, built-ins, and custom code. Tools also need resource bindings to declare and resolve their dependencies on resources.

Implementation Steps

Tool Registry and CLI
- Implement tool YAML parsing and validation (including resources section for resource slots)
- Implement agents tool add [--upgrade]/remove/list/show commands
- Implement Tool Registry persistence in database
- Implement anonymous tool support (inline definitions without registration)
Skill Registry and CLI
- Implement skill YAML parsing and validation
- Implement agents skill add [--upgrade]/remove/list/show/tools commands
- Implement hierarchical skill composition (includes) with per-tool metadata overrides
- Implement Skill Registry persistence in database
- Implement named tool references (resolving from Tool Registry) and anonymous inline tools
Tool-Resource Binding System
- Implement resource slot parsing and validation in tool YAML
- Implement three binding modes: contextual, static, parameter
- Implement binding resolution at activation time (contextual/static) and invocation time (parameter)
- Implement resource type compatibility validation
- Implement built-in tool implicit resource bindings
- Inject bound resources into ToolExecutionContext.resources

MCP Tool Adapter

class MCPToolAdapter:
    def wrap_mcp_tool(self, tool) -> Tool:
        # Add sandbox interception
        # Add change tracking
        # Add capability metadata
        # Add resource binding support

Tool Capability Metadata

class ToolCapability:
    read_only: bool
    write_scope: list[str]       # References resource slot names
    checkpointable: bool
    idempotent: bool
    side_effects: list[str]

External MCP Server Support

# In tool or skill YAML configuration
mcp_servers:
  - name: github
    command: "npx @anthropic/mcp-github"
    env: {GITHUB_TOKEN: "${GITHUB_TOKEN}"}

Agent Skills Adapter
- Implement SKILL.md frontmatter parsing for discovery
- Implement progressive disclosure (metadata → instructions → resources)
- Implement sandboxed script execution
Metadata Override System
- Implement shallow-merge override logic for tool capability metadata
- Support overrides at skill-level (tool refs), include-level (tool_overrides), and actor graph node-level
- Built-in tool metadata is not overridable

Estimated Effort: 5 weeks

8) Implement Validation and Semantic Error Prevention

Problem

Current validation is a stub. The specification requires multi-layer semantic validation.

Implementation Steps

Decision-Time Validation
- Validate choices during Strategize
- Check alternatives for feasibility
- Record validation in decision metadata

Execution-Time Guards

# Actor references a skill containing validation tools
skills:
  - local/semantic-validators   # validate_api_compatibility,
                                # check_invariants, verify_test_coverage

Project-Specific Validation

agents project set-validation \
  --project my-api \
  --test-command "pytest" \
  --lint-command "ruff check ."

Estimated Effort: 2 weeks

9) Connect LangGraph to Plan Lifecycle

Problem

The reactive/LangGraph infrastructure exists but isn't connected to the main plan workflow.

Implementation Steps

Create Unified Plan Graph

class PlanLifecycleGraph:
    def strategize_subgraph(self) -> StateGraph
    def execute_subgraph(self) -> StateGraph
    def apply_subgraph(self) -> StateGraph

Wire Phase Transitions
- use command triggers strategize graph
- execute command triggers execute graph
- apply command triggers apply graph
Remove Linear Pipeline
- Replace tell/build/apply with graph execution
- Maintain backward compatibility at CLI level

Estimated Effort: 1 week

Implementation Roadmap

Phase 1: Foundation (8-10 weeks)

Tool-based resource modification (critical foundation)
Sandbox infrastructure
Decision tree system

Phase 2: Core Systems (10-12 weeks)

Code intelligence system
Actor system with behavioral definitions
Resource system, resource types, and resource registry
MCP integration, tool system, skill system, and tool-resource bindings

Phase 3: Validation and Integration (3 weeks)

Validation and semantic error prevention
Connect LangGraph to plan lifecycle

Phase 4: Production Hardening (4 weeks)

Checkpointing and rollback
Cost controls and rate limiting
Security fixes (remove eval, fix async)

Total Estimated Timeline: 6-7 months

Key Success Metrics

Multi-file generation: Can generate a REST API with routes/, models/, tests/
Safe execution: All changes happen in sandbox, reviewed before apply
Decision correction: Can correct a decision and recompute only affected work
Scale to large codebases: Can work with 10K+ file projects efficiently
Semantic safety: Catches breaking changes before they're applied

Migration Strategy

The implementation can proceed incrementally:

Start with resource abstraction (enables everything else)
Add sandboxing to existing execute phase
Gradually replace text parsing with tool invocations
Build decision tree alongside existing flow
Enhance context as indexing comes online

This allows the system to remain functional during development while progressively adding the architectural improvements described in the specification.

CleverAgents Architecture FAQ

Q: How does CleverAgents handle persistent repository knowledge beyond ephemeral context windows?

What exists today architecturally: The specification defines a sophisticated multi-tier memory system that goes far beyond ephemeral context windows. At its core is the Decision Tree structure which provides a durable, queryable record of every choice made during planning, along with the complete context that informed those choices.

How the persistent model works in practice:

When a strategy actor analyzes a codebase during the Strategize phase, it doesn't just make decisions in isolation. Each decision creates a comprehensive Decision record that includes:

context_snapshot:
  hot_context_hash: str              # Cryptographic hash of the exact context
  hot_context_ref: str               # Pointer to the full stored snapshot
  relevant_resources: list[ResourceRef]  # Every file/symbol that influenced this decision
  actor_state_ref: str               # Complete LangGraph checkpoint

This means when the system decides "refactor the authentication module to use async patterns," it permanently records:

Which files were examined to make that decision
What symbols and dependencies were traced
The exact code state that was analyzed
The reasoning chain that led to this choice
Alternative approaches that were considered but rejected

The three-tier memory architecture enables scale:

Hot tier: Immediate working context (what's in the current LLM context window)
Warm tier: Recent decisions and their contexts from this plan tree - quickly accessible
Cold tier: Historical decisions from past plans on this codebase - queryable but not in active memory

When working on a 50,000 file codebase, the system doesn't need to hold all files in memory. Instead:

Hot context focuses on the immediate task (e.g., 10-20 files for a specific refactoring)
Warm context maintains the decision chain that got us here
Cold context provides historical patterns ("last time we refactored auth, we also had to update these services")

Why this scales to massive codebases:

The key insight is that software development is inherently local - even in huge codebases, individual changes typically touch a bounded set of files. The Decision Tree captures these localities. When converting Firefox to Rust (your example), the system would:

Make high-level architectural decisions and enforce invariants (captured as root decision nodes)
Decompose into major subsystem conversions (each a subplan_parallel_spawn or subplan_spawn decision spawning child plans)
Each subsystem plan makes decisions about its modules, inheriting applicable invariants
Module plans make decisions about individual files

At each level, only the relevant context is loaded. The persistent decision graph means we can always reconstruct why we're converting a particular module and what constraints apply from higher-level decisions.

Concrete example of persistence in action:

Plan: Convert Firefox Renderer to Rust
├── [invariant_enforced] "Maintain API compatibility with existing C++ callers"
├── [invariant_enforced] "All converted modules must pass existing C++ test suites"
├── [strategy_choice] Architecture approach: Start with leaf modules, work inward
│   Context: Analyzed module dependency graph, 2,847 modules total
│   Resources: module_graph.json, architecture_docs.md
│   
├── [subplan_parallel_spawn] Phase 1: Convert utility libraries (no external deps)
│   └── [subplan_spawn] Convert string_utils module
│       └── Plan: 01KH29R8WPKPBHRY7Q0NA9XW86
│           ├── [prompt_definition] "Convert string_utils module to Rust"
│           ├── [invariant_enforced] "Maintain API compatibility with existing C++ callers"
│           ├── [implementation_choice] Use Rust's String type, not custom implementation
│           │   Context: Analyzed 47 string_utils.cpp functions
│           │   Resources: string_utils.cpp, string_utils.h, 12 dependent files
│           │   Rationale: Rust's String provides same guarantees with better ergonomics
│           └── ...

Even months later, we can query: "Why did we use Rust's String type?" and get the exact context and reasoning, without reprocessing the entire codebase.

Q: How does the system compute task-specific dependency closures for large-scale operations?

What exists today architecturally: The specification defines multiple mechanisms for computing and maintaining minimal dependency closures. The execution blueprint produced during the Strategize phase doesn't just list steps - it includes a complete dependency graph with explicit scoping for each operation.

How dependency closure computation works:

During the Strategize phase, the strategy actor employs several mechanisms to compute precise dependency closures:

Resource-aware analysis: The actor uses specialized skills to trace dependencies:

# Pseudocode of what happens inside a strategy actor
def compute_closure_for_refactoring(target_module):
    closure = ResourceClosure()

    # Direct file dependencies
    closure.add_files(find_imports(target_module))
    closure.add_files(find_includes(target_module))

    # Symbol dependencies
    for symbol in extract_exported_symbols(target_module):
        closure.add_files(find_symbol_usage(symbol, scope='project'))

    # Test dependencies
    closure.add_files(find_tests_for_module(target_module))

    # Build system dependencies
    closure.add_files(find_build_references(target_module))

    return closure

Hierarchical scoping: When spawning child plans (via subplan_spawn or subplan_parallel_spawn), each child plan receives:
- An explicit relevant_resources list
- A sandbox_strategy appropriate for those resources
- Clear boundaries of what it can and cannot modify
- The parent plan's effective invariant view (already reconciled from action, project, and global scopes)

Decision-based tracking: Each subplan_spawn decision records the child plan it creates, and subplan_parallel_spawn decisions group parallel child plans:

# Individual child plan spawn
decision_type: subplan_spawn
chosen_option: "Refactor authentication module"
downstream_plan_ids: ["plan-auth-refactor-123"]
artifacts_produced: 
  - auth_module_files: ["auth.rs", "auth_test.rs", "auth_types.rs"]
  - api_updates: ["api/v2/login.rs", "api/v2/logout.rs"]

# Parallel group of child plans
decision_type: subplan_parallel_spawn
chosen_option: "Convert utility libraries in parallel"
# Contains subplan_spawn children, each with their own downstream_plan_ids

Concrete example - Converting a subsystem to Rust:

Let's trace how the system handles "Convert Firefox's Network Stack to Rust":

STRATEGIZE PHASE:
1. Analyze network stack structure
   - Identifies 847 C++ files in netwerk/ directory
   - Traces public API surface (237 exported functions)
   - Maps internal dependencies (1,432 internal calls)
   
2. Compute minimal closure for Phase 1 (DNS resolver):
   - Core files: dns_resolver.cpp, dns_cache.cpp, dns_config.cpp (3 files)
   - Direct dependencies: 12 files in netwerk/base/
   - Test files: 8 test files specific to DNS
   - Build files: 2 moz.build files
   - Total closure: 25 files (not 847!)
   
3. Generate execution blueprint with child plans:
   - [subplan_parallel_spawn] DNS module conversions:
     - convert-dns-types: Closure of 5 files (type definitions)
     - convert-dns-cache: Closure of 8 files (cache + tests)  
     - convert-dns-resolver: Closure of 12 files (resolver + integration)

Why this is tractable even for massive codebases:

The system leverages several key insights about real software:

Modular boundaries exist: Even in legacy codebases, there are natural boundaries
Changes are incremental: We don't convert 50,000 files atomically
Dependencies are sparse: Most modules depend on a small fraction of the codebase
Interfaces are narrow: Public APIs are much smaller than implementations

The Firefox example would decompose into ~1,000 bounded child plans (grouped via subplan_parallel_spawn decisions where independent), each touching 10-100 files. The parent plan tracks the overall architecture and enforces invariants, while each child plan maintains its focused closure.

How we prevent closure explosion:

Lazy expansion: Dependencies are traced only as deep as needed for correctness
Interface-based boundaries: When possible, work against stable interfaces
Incremental validation: Each child plan validates its changes don't break dependents
Hierarchical merge strategies: Parent plans resolve conflicts between child plan changes

Q: What mechanisms enforce global consistency during parallel execution across many files?

What exists today architecturally: The sandbox model combined with hierarchical plan execution provides strong guarantees about consistency during parallel execution. This isn't just process isolation - it's semantic isolation with intelligent merge strategies.

How the coordination mechanism prevents compound errors:

Complete isolation during execution: Each plan executes in its own sandbox, which means:

Plan A (refactoring auth module):
- Sandbox A1: Contains only auth/*.cpp, auth_tests/*.cpp
- Cannot see Plan B's intermediate states
- Cannot accidentally depend on Plan B's half-done work

Plan B (updating API endpoints):
- Sandbox B1: Contains only api/*.cpp, api_tests/*.cpp  
- Makes changes assuming current auth interface
- Protected from Plan A's intermediate refactoring

Resource-specific sandbox strategies provide natural coordination:

Git repositories:
  - Strategy: git worktrees
  - Coordination: Git's three-way merge algorithm
  - Conflict detection: Built into Git
  - Rollback: git reset/checkout

Databases:
  - Strategy: Transaction isolation  
  - Coordination: MVCC (multi-version concurrency control)
  - Conflict detection: Serialization failures
  - Rollback: Transaction abort

Cloud Infrastructure:
  - Strategy: Terraform workspaces
  - Coordination: State locking
  - Conflict detection: Resource conflicts in plan
  - Rollback: Previous state restoration

Hierarchical merge resolution: When child plans complete, the parent plan performs intelligent merging:

def merge_subplan_results(subplan_results):
    # Group by resource type
    by_resource = group_by_resource_type(subplan_results)

    # Apply resource-specific merge strategies
     for resource_type, changes in by_resource:
         if resource_type == 'git-checkout':
             merge_git_changes(changes)  # Three-way merge
         elif resource_type == 'fs-mount':
             merge_fs_changes(changes)   # Copy-on-write reconciliation
         elif resource_type.startswith('database'):
             merge_db_changes(changes)   # Sequential application

    # Validate merged state
    run_integration_tests()

Concrete example - Preventing cascading failures:

Consider refactoring a shared authentication library used by 15 services:

PARALLEL EXECUTION WITHOUT COORDINATION (what we prevent):
- Service A refactors to async auth → breaks Service B
- Service B compensates with workaround → breaks Service C  
- Service C changes error handling → breaks Services D, E, F
- Cascade of failures!

CLEVERAGENTS COORDINATED EXECUTION:
Parent Plan: Refactor auth library
├── [invariant_enforced] "Auth library public API must remain backward compatible during transition"
├── [subplan_spawn] Plan 1: Update auth library interface
│   Sandbox: Only auth library files
│   Output: New interface definition
│   
├── Barrier: Wait for Plan 1 completion
│   
├── [subplan_parallel_spawn] Plans 2-16: Update each service (in parallel)
│   Each sandbox: Only that service's files
│   Each uses: New interface from Plan 1
│   No inter-service dependencies during execution
│   
└── Merge Phase:
    - Collect all service updates
    - Apply to main branch in order
    - Run integration tests
    - If conflicts: Parent plan resolves using semantic understanding

Advanced coordination patterns:

Optimistic concurrency with semantic conflict resolution:

Two child plans both modify api/user.rs:
- Plan A: Adds async fn get_user_profile()
- Plan B: Adds fn validate_user_permissions()

Merge strategy:
- Git merge succeeds (different functions)
- Semantic validation ensures both functions work together
- Parent plan adds integration glue if needed

Checkpoint-based coordination:

Execution timeline:
T1: Plan A creates checkpoint before major refactor
T2: Plan B creates checkpoint before API changes
T3: Plan A encounters error, rolls back to T1
T4: Plan B completes successfully
T5: Plan A retries with knowledge of B's success

Resource locking for critical sections:

When modifying shared schema files:
- Acquire exclusive lock on schema resources
- Make changes atomically
- Release lock with new version
- Other plans rebase on new schema

Q: How does the system proactively prevent semantic errors before they propagate?

What exists today architecturally: The specification defines multiple layers of proactive error prevention that go far beyond traditional testing. This is a comprehensive defense-in-depth approach that catches semantic errors before they can propagate.

Layer 1: Decision-time validation during Strategize:

Every decision includes semantic validation:

Decision: Refactor payment module to async
alternatives_considered:
  - "Convert to async/await patterns" (chosen)
  - "Use thread pool with channels" (rejected: doesn't integrate with async ecosystem)
  - "Keep synchronous with timeout" (rejected: doesn't solve core latency issue)
confidence_score: 0.85
validation_performed:
  - Checked all payment API consumers can handle async
  - Verified database driver supports async operations
  - Confirmed no regulatory requirement for sync processing

Layer 2: Execution-time semantic guards:

The execution actor uses a tool node that references the independently registered local/validate-api-compat tool:

actors:
  code_executor:
    type: graph
    skills:
      - local/semantic-validators    # Contains validation tools for LLM tool-calling
    nodes:
      - name: semantic_validator
        type: tool
        tool: local/validate-api-compat   # Named tool from Tool Registry

The local/validate-api-compat tool (independently registered via agents tool add) performs semantic validation — not just syntax checking. It extracts API signatures, finds breaking changes, checks affected consumers, and either auto-migrates or raises a SemanticError for manual review.

Layer 3: Invariant enforcement through the decision tree:

Invariants are attached at four scopes (global, project, action, plan) and managed via the unified agents invariant command or --invariant flags on creation commands. When a plan enters Strategize, the Invariant Reconciliation Actor (set via --invariant-actor on actions/plans/projects, or globally via agents config set invariant-actor) computes the effective invariant view by applying precedence rules (plan > project > global) to resolve conflicts. Each effective invariant is recorded as an invariant_enforced decision, making them visible, correctable, and auditable:

# The system collects, reconciles, and enforces semantic invariants
class InvariantEnforcer:
    def compute_effective_invariants(self, plan):
        """Compute the effective invariant view using the Invariant Reconciliation Actor."""
        raw = self.collect_all_invariants(plan)
        reconciler = (
            self.get_plan_invariant_actor(plan)
            or self.get_project_invariant_actor(plan)
            or self.get_global_invariant_actor()
        )
        # Apply precedence: plan > project > global
        return reconciler.reconcile(raw, precedence=['plan', 'project', 'global'])
    
    def collect_all_invariants(self, plan):
        """Collect invariants from all scopes accessible to this plan."""
        invariants = []
        invariants.extend(self.get_global_invariants())
        for project in plan.projects:
            invariants.extend(self.get_project_invariants(project))
        invariants.extend(self.get_action_invariants(plan.action))
        invariants.extend(self.get_plan_invariants(plan))
        return invariants
    
    # Example invariants at different scopes:
    # Global:  "Payment processing must be idempotent"
    # Project: "Database transactions must complete within 5 seconds"
    # Action:  "Test files must not import production secrets"
    # Plan:    "All API calls over TCP must be mocked"
    
    def check_invariant_preservation(self, changes, enforced_invariants):
        for invariant in enforced_invariants:
            if not self.verify_invariant(invariant, changes):
                return InvariantViolation(invariant, changes)
        return Success()

Layer 4: Predictive error prevention through pattern matching:

The system learns from past failures:

Error Pattern Database:
  - pattern: "Async conversion in payment module"
    historical_failures:
      - "Race condition in payment confirmation"
      - "Timeout handling breaks idempotency"
    preventive_checks:
      - "Add explicit transaction boundaries"
      - "Verify idempotency keys are preserved"
      - "Check distributed lock acquisition"

Concrete example - Preventing a subtle distributed systems bug:

Scenario: Refactoring a service to use event sourcing:

PROACTIVE CONTAINMENT IN ACTION:

1. Strategy Phase Semantic Analysis:
   - Decision: "Convert order service to event sourcing"
   - Semantic check: "Event sourcing requires eventual consistency"
   - Identifies: 3 services assume immediate consistency
   - Adds decision: "Update dependent services for eventual consistency"

2. Execution Phase Invariant Checking:
   - Detects: PaymentService.chargeCard() called after OrderCreated event
   - Semantic issue: Payment before order confirmation violates business rules
   - Automatic fix: Insert OrderConfirmed event requirement
   
3. Validation Node Catches Edge Case:
   - Discovers: Audit service expects synchronous order numbers
   - Impact: Async events break compliance reporting
   - Resolution: Add audit event buffer with guaranteed ordering
   
4. Pre-Apply Semantic Verification:
   - Simulates production event flow
   - Detects: Under high load, events can arrive out of order
   - Adds: Event ordering guarantees via vector clocks

Why this prevents issues that traditional testing misses:

Traditional tests check "does the code work?" Our semantic containment asks:

Does it preserve business invariants?
Does it maintain architectural patterns?
Does it respect distributed systems principles?
Does it handle the edge cases we've seen before?

Integration with Definition of Done (DoD):

Each plan's DoD includes semantic requirements:

definition_of_done:
  must:
    - "All API changes maintain backward compatibility"
    - "No increase in p99 latency"
    - "Audit trail remains complete"
  should:
    - "Improve code coverage by 10%"
    - "Reduce cyclomatic complexity"
  may:
    - "Optimize for memory usage"

The validation nodes enforce these semantics, not just test passage.

Q: How does the system balance human supervision with autonomous operation?

What exists today architecturally: The specification defines a sophisticated gradation of automation levels that precisely controls when human intervention is needed. This isn't a binary human/AI split - it's a spectrum that can be adjusted per task, per project, or per organization.

How the automation levels work in practice:

Manual Mode:
  - Every decision point pauses for human input
  - User sees: Context, alternatives, recommendation
  - User provides: Explicit choice or custom guidance
  - Use case: Critical production changes, learning new codebases

Review-before-apply Mode:
  - AI makes all decisions autonomously
  - Execution completes in sandbox
  - Human reviews complete diff before apply
  - User can: Approve, reject, or correct specific decisions
  - Use case: Normal feature development, refactoring

Full Automation Mode:
  - AI makes all decisions
  - Execution proceeds through apply
  - Human notified of completion
  - Rollback available if issues detected
  - Use case: Routine updates, test generation, documentation

The decision correction mechanism enables progressive automation:

The agents plan correct command is crucial for building trust:

# User observes AI made suboptimal choice
agents plan tree <plan_id>
# Sees: [Decision] "Use REST API for service communication"

# User knows gRPC would be better for this use case
agents plan correct <decision_id> --mode=revert \
  --guidance "Use gRPC instead of REST. This service requires streaming 
             updates and binary protocol efficiency. Set up protocol 
             buffer definitions and generate client/server stubs."

# System:
# 1. Marks original decision as superseded
# 2. Creates new decision with user guidance
# 3. Recomputes ONLY affected downstream decisions
# 4. Preserves all unrelated work

Progressive trust building through automation levels:

New users typically follow this progression:

Start with manual mode to understand system behavior
Move to review-before-apply as confidence builds
Enable full automation for specific task types
Gradually expand full automation scope

Real autonomy through semantic understanding:

True autonomy isn't about removing humans - it's about the system understanding when it needs help:

class AutonomyController:
    def assess_decision_confidence(self, decision, context):
        factors = {
            'past_success_rate': self.get_historical_success(decision.type),
            'codebase_familiarity': self.get_familiarity_score(context.project),
            'risk_assessment': self.evaluate_risk(decision),
            'invariant_complexity': self.analyze_invariants(decision)
        }
        
        confidence = self.compute_confidence(factors)
        
        if confidence < self.threshold:
            if self.automation_level == 'full':
                # Even in full automation, critical decisions escalate
                return RequestHumanGuidance(decision, factors)
        
        return ProceedAutonomously(decision)

Concrete example - Autonomous handling of a complex refactoring:

Scenario: "Modernize legacy e-commerce system"

INITIAL PLAN (Full Automation Mode):
1. System analyzes 50,000 line codebase
2. Identifies modernization opportunities
3. Creates plan with 47 child plans

AUTONOMOUS EXECUTION WITH SMART ESCALATION:

[subplan_parallel_spawn] Plans 1-15: Update utility functions (executes autonomously)
- Confidence: 0.95 (straightforward transformations)
- Result: Success

[subplan_spawn] Plan 16: Refactor payment processing
- Confidence: 0.4 (critical business logic)
- [invariant_enforced] "Preserve exact penny rounding behavior"
- Action: ESCALATES to human
- Human provides: "Preserve exact penny rounding behavior"
- Continues autonomously with constraint

[subplan_parallel_spawn] Plans 17-30: UI component updates (executes autonomously)
- Confidence: 0.9 (isolated changes)
- Result: Success

[subplan_spawn] Plan 31: Database schema migration
- Detects: Would require 6-hour downtime
- Action: ESCALATES to human
- Human provides: "Use online migration with feature flags"
- Re-plans with zero-downtime approach

[subplan_parallel_spawn] Plans 32-47: Complete autonomously

The path to greater autonomy:

The system becomes more autonomous through:

Learning from corrections:
- Every correction teaches the system about user preferences
- Patterns emerge: "This team always prefers gRPC for microservices"
- Future decisions incorporate these learnings
Building project-specific context:
- Each successful plan adds to project knowledge
- System learns codebase patterns, team conventions, business rules
- Confidence increases with familiarity
Hierarchical delegation:
- Proven child plan patterns become fully autonomous
- Human focuses on high-level decisions
- System handles implementation details
Semantic safety nets:
- Comprehensive invariant checking reduces risk
- Rollback capabilities provide recovery path
- Humans can trust system won't cause catastrophic failures

Q: What's actually implemented today versus planned for the future?

Concrete implementations in the architecture:

Decision Tree with Complete Context Capture
- Full schema defined
- Storage model specified
- Correction mechanism detailed
- Query patterns established
Hierarchical Plan System
- Spawning mechanism defined (sequential subplan_spawn and parallel subplan_parallel_spawn)
- Execution semantics specified (child plans are full Plans with their own decision trees)
- Invariant inheritance from parent plans, projects, and global scope
- Merge strategies documented
- Failure handling described
Resource-Aware Sandbox Isolation
- Multiple strategies defined (git worktree, filesystem overlay, transactions)
- Lazy sandboxing for efficiency
- Resource-specific merge algorithms
- Cleanup behavior specified
Multi-Layer Error Prevention
- Decision validation during planning
- Semantic validation nodes
- Invariant enforcement
- Definition of Done checking
Graduated Automation Controls
- Three levels clearly defined
- Decision correction without full re-execution
- Confidence-based escalation
- Progressive trust building

Near-term implementations (architecture complete, engineering straightforward):

Memory Tier Management
- Hot/warm/cold distinction clear
- Context loading patterns defined
- Just needs LRU cache and storage backend
Cross-Plan Learning
- Decision history provides training data
- Pattern extraction is standard ML
- Confidence scoring is well-understood
Cost/Risk Estimation
- Dedicated estimation actor role defined
- Historical data provides baselines
- Standard prediction problem
Extended Validation Patterns
- Pluggable validation architecture
- Project-specific rules as configuration
- Industry patterns can be packaged

Research territory (requires innovation but architecture supports):

Optimal Context Selection for 100K+ file codebases
- Current: Heuristic-based selection
- Research: ML-driven relevance ranking
- Architecture supports: Any selection algorithm can plug in
Automated Invariant Discovery
- Current: User-defined invariants
- Research: Mining invariants from code patterns
- Architecture supports: Invariants are just validation rules
Cross-Project Knowledge Transfer
- Current: Project-specific learning
- Research: Generalized pattern recognition
- Architecture supports: Cold tier can span projects
Fully Autonomous Recovery Strategies
- Current: Rollback and retry with guidance
- Research: Automatic error understanding and fixing
- Architecture supports: Recovery is just another plan type

Why we can confidently handle Firefox-scale projects:

The architecture doesn't require magical AI breakthroughs. It requires:

Hierarchical decomposition: ✓ Fully specified
Bounded context operations: ✓ Dependency closure computation defined
Parallel execution with isolation: ✓ Sandbox model complete
Semantic validation: ✓ Multi-layer approach specified
Progressive automation: ✓ Automation levels and correction defined

The difference between handling a 1,000 file project and a 100,000 file project is:

More child plans (hierarchical decomposition handles this)
Larger cold storage (standard database scaling)
Better context selection (improves with use but works with heuristics)
More validation patterns (accumulate over time)

This isn't speculative architecture astronautics - it's applying proven distributed systems principles to AI agent coordination. The innovation is in the integration, not in requiring fundamental breakthroughs.

513 KiB Raw Blame History Unescape Escape

CleverAgents Documentation (Detailed Spec)

Key Themes

Big Picture: What CleverAgents is

Glossary (Terms Used Precisely)

CLI Commands

Command Synopsis

Command Reference

Global Options

agents version

agents info

agents diagnostics

agents init

agents session

agents session create

agents session list

agents session show

agents session delete

agents session export

agents session import

agents session tell

agents project

agents project create

agents project link-resource

agents project unlink-resource

agents project list

agents project show

agents project set-validation

agents project delete

agents project context

agents project context set

agents project context show

agents actor

agents actor run

agents actor add

agents actor update

agents actor remove

agents actor list

agents actor show

agents actor set-default

agents actor context

agents actor context add

agents actor context load

agents actor context rm

agents actor context list

agents actor context show

agents actor context export

agents actor context import

agents actor context delete

agents actor context clear

agents skill

agents skill add

agents skill remove

agents skill list

agents skill show

agents skill tools

agents tool

agents tool add

agents tool remove

agents tool list

agents tool show

agents resource type

agents resource type add

agents resource type remove

agents resource type list

agents resource type show

agents resource

agents resource add

agents resource remove

agents resource list

agents resource show

agents resource tree

agents resource link-child

agents resource unlink-child

agents plan

agents plan list

agents plan use

agents plan execute

agents plan apply

agents plan status

513 KiB

Raw Blame History

1) `name` (namespaced)

2) `short_description`

3) `long_description`

4) `definition_of_done` (DoD)

5) `actors`

6) `reusable` (boolean)

7) `read_only` (boolean)

8) `inputs_schema` (recommended addition)

9) `safety_profile` (recommended addition)

1) `projects`

2) `strategy_context`

3) `strategy`

4) `execution_blueprint` (recommended addition)

5) `cost_estimate` and `risk_estimate` (optional)