Files
cleveragents-core/docs/reference/actor_cli.md
T
HAL9000 18d00c04c4
CI / lint (pull_request) Failing after 1m15s
CI / quality (pull_request) Successful in 1m21s
CI / typecheck (pull_request) Successful in 1m34s
CI / security (pull_request) Successful in 1m37s
CI / coverage (pull_request) Has been skipped
CI / unit_tests (pull_request) Failing after 1m37s
CI / docker (pull_request) Has been skipped
CI / build (pull_request) Successful in 33s
CI / helm (pull_request) Successful in 26s
CI / push-validation (pull_request) Successful in 19s
CI / e2e_tests (pull_request) Successful in 3m20s
CI / integration_tests (pull_request) Successful in 4m32s
CI / status-check (pull_request) Failing after 3s
fix(skills): implement multi-scope agent skill discovery for global, project, and local tiers
Implements AgentSkillDiscovery class to support discovering Agent Skills from
multiple configured directories across three scopes (global, project, local).
Handles name collisions with precedence: local > project > global.

Adds comprehensive BDD test coverage for multi-scope discovery scenarios including:
- Global-only, project-only, and local-only discovery
- Combined discovery from all scopes
- Name collision resolution with proper precedence
- Non-existent and empty scope directory handling
- Multiple skills in same scope discovery

ISSUES CLOSED: #9369
2026-05-06 19:55:22 +00:00

5.0 KiB

Actor CLI Reference

The agents actor command group manages actor configurations for the CleverAgents v3 actor system.

Commands

Command Description
agents actor add Add actor from YAML/JSON config file
agents actor update Update an existing actor
agents actor remove Remove a custom actor by namespaced name
agents actor list List all registered actors
agents actor show Show actor details
agents actor set-default Set the default actor
agents actor run Run the reactive network with actor configs

Namespaced Names

Actor names follow the [[server:]namespace/]name format. When no namespace is provided, the name defaults to local/. Built-in actors use <provider>/<model> (e.g. openai/gpt-4).

agents actor add

Add a new actor from a YAML or JSON configuration file.

Synopsis

agents actor add <NAME> --config <FILE> [--update] [--unsafe] [--set-default] [--option key=value] [--format FORMAT]

YAML Configuration File

provider: openai
model: gpt-4
temperature: 0.7
max_tokens: 1024
options:
  stream: true

Examples

# Add an actor from YAML config
agents actor add local/my-actor --config ./actors/my-actor.yaml

# Add or update an existing actor
agents actor add local/my-actor --config ./actors/my-actor.yaml --update

# Add with option overrides
agents actor add local/my-actor --config actor.yaml --option temperature=0.9

# Add with JSON output
agents actor add local/my-actor --config actor.yaml --format json

agents actor update

Update an existing actor configuration.

Synopsis

agents actor update <NAME> [--config <FILE>] [--unsafe|--safe] [--set-default] [--option key=value] [--format FORMAT]

Examples

# Update actor with new config
agents actor update local/my-actor --config ./actors/updated.yaml

# Mark actor as safe
agents actor update local/my-actor --safe

# Update with JSON output
agents actor update local/my-actor --format json

agents actor remove

Remove a custom actor by its namespaced name.

Synopsis

agents actor remove <NAME>

Rich Output Panels

After removal, the rich format renders three panels:

  • Actor Removed — name, provider, and model of the removed actor.
  • Impact — number of sessions, active plans, and actions that referenced the actor.
  • Cleanup — config retention status and number of orphaned contexts.

Followed by a ✓ OK Actor removed success message.

Examples

agents actor remove local/my-actor

agents actor list

List all registered actors.

Synopsis

agents actor list [--format FORMAT]

Output Formats

Format Description
rich Rich table with colours (default)
json JSON array of actor objects
yaml YAML list of actor objects
plain Plain text key-value pairs
table ASCII table without Rich styling

Rich Output

The rich format renders a table with columns: Name, Provider, Model, Default, Built-in, Unsafe, and Updated. After the table, a Summary panel is shown with:

Field Description
Total Total number of actors
Built-in Count of built-in actors
Custom Count of custom actors
Unsafe Count of actors marked unsafe
Providers Used Number of distinct providers

Followed by a ✓ OK N actors listed success message.

Examples

# Default rich table
agents actor list

# JSON output for scripting
agents actor list --format json

# YAML output
agents actor list --format yaml

agents actor show

Show details for a specific actor.

Synopsis

agents actor show <NAME> [--format FORMAT]

Examples

# Rich panel (default)
agents actor show local/my-actor

# JSON output
agents actor show local/my-actor --format json

# YAML output
agents actor show openai/gpt-4 --format yaml

agents actor set-default

Set the default actor used when no actor is specified.

Synopsis

agents actor set-default <NAME>

Examples

agents actor set-default openai/gpt-4

Error Handling

Error Cause
Config file not found Specified config file doesn't exist
Config must be a JSON/YAML object Config file is not a valid object
Config file is required No --config flag provided for add
Actor config is marked unsafe Unsafe config without --unsafe flag
Actor not found Named actor doesn't exist