docs(development): add developer setup guide

Add comprehensive developer setup guide covering prerequisites, development workflow, testing, linting, type checking, commit guidelines, devcontainer setup, and troubleshooting. Refs: #9123
fix(agents): make bug-hunt-pool-supervisor tracking non-blocking to prevent initialization hangs
2026-04-14 08:12:26 +00:00 · 2026-04-14 05:25:30 +00:00
108 changed files with 794 additions and 1889 deletions
@@ -9,10 +9,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: "#E74C3C"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -104,7 +100,7 @@ Poll every 30 minutes using `bash("sleep 1800", timeout=1860000)`.
 - Prefix: `AUTO-EVLV`
 - Cycle interval: ~30 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Never apply changes directly.** All changes go through the two-step proposal workflow.
 2. **Evidence-based only.** Every proposal must cite specific failure data.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -64,7 +60,7 @@ Your prompt describes the approved proposal: what change to make, and the eviden
 5. Create a PR using `pr-creator` with `needs feedback` label.
 6. Clean up and exit.

-## **CRITICAL** Rules
+## Rules

 1. **One change, then exit.**
 2. **Only modify `.opencode/agents/` files.** Never modify source code.
@@ -11,10 +11,6 @@ hidden: true
 temperature: 0.1
 model: anthropic/claude-haiku-4-5
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -444,7 +440,7 @@ Look up the target prefix's matrix entry. Find the source prefix in the table. R
 ### For DYNAMIC_RELEVANCY
 Invoke `agent-type-info` to learn about the agent's purpose and relationships. Then reason about functional dependencies to construct a relevancy table following the same patterns as the static matrix.

-## **CRITICAL** Rules
+## Rules

 1. **Prefix format**: All autonomous system prefixes start with `AUTO-` and are enclosed in square brackets when used as session tags: `[AUTO-XYZ]`.
 2. **Universal baseline**: Every agent, regardless of its role, should consume all announcements at Priority/Critical+ at minimum. This is non-negotiable.
@@ -9,10 +9,6 @@ hidden: true
 temperature: 0.0
 model: openai/gpt-5-nano
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -466,7 +462,7 @@ Files in `shared/` are included in other agents' prompts, not standalone agents:
 | shared/session_state | Session state management. |
 | shared/tracking_discovery_guide | Tracking issue discovery patterns. |

-## **CRITICAL** Rules
+## Rules

 1. **Respond factually.** Only provide information that is in this catalog. If asked about an agent that doesn't exist, say so.
 2. **Be concise.** When listing agents, use table format. When describing one agent, use the structured format above.
@@ -10,10 +10,6 @@ temperature: 0.1
 model: google/gemini-2.5-pro
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -95,7 +91,7 @@ Findings create `Type/Refactor` issues with `State/Unverified`.
 - Prefix: `AUTO-GUARD`
 - Cycle interval: ~10 minutes

-## **CRITICAL** Rules
+## Rules

 1. **SHA-based idle detection.** Don't scan when master hasn't changed.
 2. **Never scan yourself.** Dispatch workers for all scanning.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.1
 model: google/gemini-2.5-pro
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -62,7 +58,7 @@ Your prompt tells you to perform a full codebase scan. You must:
 4. Check for existing issues before filing to avoid duplicates.
 5. Clean up and exit.

-## **CRITICAL** Rules
+## Rules

 1. **One scan, then exit.**
 2. **Check for duplicates.** Search existing issues before filing.
@@ -10,10 +10,6 @@ temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 color: primary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -110,7 +106,7 @@ When the spec grows beyond approximately 3,000 lines, workers should transition
 - Prefix: `AUTO-ARCH`
 - Cycle interval: ~30 minutes

-## **CRITICAL** Rules
+## Rules

 1. **You are the most consequential agent.** Bad architecture cascades everywhere. Be thoughtful.
 2. **Major changes need human approval.** Always use the `needs feedback` label for major changes.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -67,7 +63,7 @@ Your prompt tells you what specification section to write or update, whether thi

 When the spec exceeds ~3,000 lines, split into `docs/specification/` with one file per module.

-## **CRITICAL** Rules
+## Rules

 1. **One task, then exit.**
 2. **Follow CONTRIBUTING.md commit and PR standards** as provided in your prompt.
@@ -8,10 +8,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: success
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -65,7 +61,7 @@ Your prompt includes:
 4. Include setup and teardown methods where needed.
 5. Return a summary of benchmarks written.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.**
 2. **Benchmarks in `benchmarks/` only.**
@@ -8,10 +8,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#DC2626"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -49,6 +45,6 @@ You shut down multiple async agent sessions. Your caller provides a tag pattern
 2. For each matching session, invoke `async-agent-manager` to delete it.
 3. Report a summary: how many sessions were deleted, how many failed, and any errors.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* the session list returned by `async-agent-manager` when searching for sessions by pattern must be fully paginated — there may be more sessions than fit in the first response; always confirm all matching sessions are found before reporting the cleanup count.
@@ -8,10 +8,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#DC2626"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -48,6 +44,6 @@ You shut down a specific async agent session. Your caller provides the session I
 1. Invoke `async-agent-manager` to delete the specified session.
 2. Report the result (success or failure with reason).

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* if `async-agent-manager` is called to list sessions to find one by tag before deleting it, that session list must be fully paginated to ensure the correct session is found.
@@ -10,10 +10,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#DC2626"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -223,7 +219,7 @@ If the server is unreachable or returns errors:
 - Report the failure clearly to the caller with the HTTP status code and response body.
 - Never silently swallow errors.

-## **CRITICAL** Rules
+## Rules

 1. **You are the only agent that calls localhost:4096.** No other agent has this permission.
 2. **Always escape prompt text for JSON.** Use `jq -Rs .` to properly escape strings before embedding in JSON.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#DC2626"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -59,6 +55,6 @@ A session is **stuck** if it has `busy` status but no message activity for more

 If the caller requests a restart for a stuck/errored session, invoke `async-agent-manager` to stop the old session and launch a new one with the same tag and agent type.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* when `async-agent-manager` returns a list of sessions for health checking, ensure all sessions are retrieved (paginate if needed); when fetching messages from a session, use the highest available `limit` and paginate to get the full message history for accurate health assessment.
@@ -10,10 +10,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: secondary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -57,7 +53,7 @@ Creates a new status tracking issue for a cycle. Closes ALL existing open status
 Parameters from caller: `agent-prefix`, `tracking-type`, `body`, `sleep-interval-default`, `repo-owner`, `repo-name`

 Steps:
-1. Search for all open issues with label `Automation Tracking` whose title starts with `[{agent-prefix}] Status:`. For example if the `agent-prefix` is `AUTO-IMP-SUP` then you'd search for titles starting with `[AUTO-IMP-SUP] Status:`.
+1. Search for all open issues with label `Automation Tracking` whose title starts with `[{agent-prefix}] Status:`.
 2. **CRITICAL** Close every one found (post comment "Superseded by next cycle" before closing).
 3. Determine next cycle number: search ALL issues (open and closed) with the same prefix, find the highest cycle number, add 1.
 4. Determine next estimated cycle interval: use the issue identified in step 3 above, take its reported estimated cycle interval, then using the rolling average formula: if a previous issue exists, `round(old_interval * 0.90 + actual_interval * 0.10)`, otherwise use `sleep-interval-default`.
@@ -161,7 +157,7 @@ Parameters: `agent-prefix`
 3. Based on the results returned in step 1, filter by the agent prefix and priority level listed. The priority should be determined by looking at the labels on the issue, the agent type should be filtered by looking at the tag in the title, for example if you are filtering on the implementation pool supervisor then youd look for titles that start with `[AUTO-IMP-SUP]`.
 4. Return the complete filtered list of announcements including their title, body, metadata (like labels and milestone) as well as all comments on the announcement. If there are no announcements that matched simply explain that in your response.

-## **CRITICAL** Rules
+## Rules

 1. **One status issue at a time.** Always close ALL existing before creating new.
 2. **Cycle numbers are globally unique per prefix.** Search ALL issues (including closed) to find the next number.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -89,7 +85,7 @@ Never run `behave` directly.
 5. Fix any failures and re-run until green.
 6. Return a summary of tests written.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.** Always work in the provided `/tmp/` working directory.
 2. **One subtask, then exit.**
@@ -8,10 +8,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: secondary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -70,6 +66,6 @@ git -C "$WORK_DIR" rebase origin/master

 Return the branch name and whether it was newly created or already existed.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `git branch -r` listing remote branches may be long — do not stop processing at an assumed cutoff; any `git log` output may be truncated by terminal pagination — use `--no-pager` or explicit limits.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: google/gemini-2.5-pro
 color: error
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -95,7 +91,7 @@ Each cycle:

 4. **Monitor workers.** Count active workers, check for stuck sessions.

-5. **Update tracking.** Every 3 cycles, create a status tracking issue via `automation-tracking-manager` with prefix `AUTO-BUG-POOL`.
+5. **Update tracking (non-blocking).** Every 3 cycles, attempt to create a status tracking issue via `automation-tracking-manager` with prefix `AUTO-BUG-POOL`. This step is **best-effort** — if the call does not complete within a reasonable time or fails, skip it and continue to the next cycle. **Never block the main loop waiting for tracking.** Tracking is informational only; the supervisor's core function (module scanning and worker dispatch) must continue regardless.

 ## Finding Validation Gate

@@ -114,7 +110,7 @@ Workers use the `new-issue-creator` subagent to file validated findings.
 - Prefix: `AUTO-BUG-POOL`
 - Cycle interval: ~15 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Validate before filing.** All five validation checks must pass.
 2. **Check for existing issues and PRs.** Never file a duplicate.
@@ -130,3 +126,4 @@ Supervisor: Bug Hunt Pool | Agent: bug-hunt-pool-supervisor

 7. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 8. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_issues` (default 20 — use `limit=50` and paginate to check for all existing bug issues before filing duplicates); `forgejo_list_repo_pull_requests` (same — check all open PRs that may already address a discovered bug).
+9. **Tracking is non-blocking.** The `automation-tracking-manager` call in step 5 must never block the main loop. If it hangs or fails, skip it and proceed. Core functionality (module mapping, worker dispatch, monitoring) takes priority over status reporting.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.1
 model: google/gemini-2.5-pro
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -71,7 +67,7 @@ Your prompt tells you which module to analyze and provides the relevant specific
 4. File validated findings using `new-issue-creator`.
 5. Clean up your clone and exit.

-## **CRITICAL** Rules
+## Rules

 1. **One module, then exit.** Do not analyze additional modules.
 2. **All five validation checks must pass.** No exceptions.
@@ -7,7 +7,6 @@ mode: primary
 temperature: 0.1
 color: accent
 permission:
-  "doom_loop": deny
  edit: allow
  webfetch: allow
  bash:
@@ -6,7 +6,6 @@ mode: primary
 temperature: 0.2
 color: primary
 permission:
-  "doom_loop": deny
  edit: allow
  webfetch: allow
  bash:
@@ -9,10 +9,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#6B7280"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -90,7 +86,7 @@ A structured summary of CI failures:
 - **Error details** — specific error messages, test names, line numbers
 - **Category** — lint failure, typecheck failure, unit test failure, integration test failure, build failure

-## **CRITICAL** Rules
+## Rules

 1. **Credentials from prompt only.** Never read environment variables.
 2. **Clean up cookies.** Always delete the cookie jar file after use.
@@ -9,10 +9,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: secondary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -72,6 +68,6 @@ ISSUES CLOSED: #42

 The first line MUST be the exact text from the issue metadata. The body is the contributor's description. The footer references the issue.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* this agent makes no direct paginated list calls, but any future tool or REST calls returning arrays must be paginated.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -60,7 +56,7 @@ You analyze test coverage and write new Behave tests to reach the 97% threshold.
 6. Repeat until coverage is at or above 97%.
 7. Return a summary of tests added and the final coverage percentage.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.**
 2. **BDD tests only.** Write Behave features, never xUnit tests.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-haiku-4-5
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -60,6 +56,6 @@ You evaluate a subtask's difficulty and recommend a starting model tier. When un
 - **reasoning** — brief explanation of why this tier
 - **confidence** — how confident you are in the assessment (high/medium/low)

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* bash `find` or `wc` commands over source files must not assume all files are captured; any future REST/curl calls returning JSON arrays must be paginated.
@@ -9,10 +9,6 @@ temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 color: "#9B59B6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -83,7 +79,7 @@ Workers extend existing documentation rather than overwriting it.
 - Prefix: `AUTO-DOCS`
 - Cycle interval: ~30 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Extend, don't overwrite.** Always read existing docs and add to them.
 2. **Never create docs yourself.** Dispatch workers for all writing.
@@ -7,10 +7,6 @@ hidden: true
 temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -63,7 +59,7 @@ Your prompt describes the documentation task (e.g., "update README for milestone
 4. Create a PR using `pr-creator`.
 5. Clean up and exit.

-## **CRITICAL** Rules
+## Rules

 1. **One task, then exit.**
 2. **Extend, don't overwrite.** Always read existing docs and add to them.
@@ -9,10 +9,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: accent
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -114,7 +110,7 @@ Child issues BLOCK their parent Epic. The Epic DEPENDS ON its children. This mea
 - Prefix: `AUTO-EPIC`
 - Cycle interval: ~10 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Follow CONTRIBUTING.md issue format exactly.** Every issue needs: metadata, subtasks, definition of done, proper labels, milestone.
 2. **Correct dependency direction.** Child BLOCKS parent. Always.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -60,7 +56,7 @@ Your prompt describes the planning task: which Epic to decompose, which issues t
 4. Post a comment on the parent Epic listing its new children.
 5. Exit.

-## **CRITICAL** Rules
+## Rules

 1. **One batch, then exit.**
 2. **Follow CONTRIBUTING.md issue format exactly.** Every issue needs metadata, subtasks, DoD.
@@ -8,10 +8,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -53,6 +49,6 @@ You generate a comprehensive final report summarizing all work completed across
 4. **Quality Statistics** — test pass rates, coverage, lint/typecheck status
 5. **Problems Encountered** — any blockers, human escalations, or recurring issues

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_milestones` (paginate to get all milestones for the summary); `forgejo_list_repo_issues` (use `limit=50` and paginate all pages — an incomplete count would corrupt the final report statistics); `forgejo_list_repo_pull_requests` (same — all merged PRs must be counted).
@@ -7,10 +7,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: "#059669"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -71,7 +67,7 @@ You manually fix a specific pull request. The user tells you which PR to fix. Yo
 6. Commit and push using `git-commit-helper`.
 7. Clean up the isolated clone using `repo-isolator`.

-## **CRITICAL** Rules
+## Rules

 1. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 2. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_pull_reviews` (use `limit=50` and paginate to read ALL reviewer feedback before fixing); `forgejo_list_workflow_runs` (paginate to find the latest CI run for the PR's head commit).
@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: "#9B59B6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -98,7 +94,7 @@ When applying a label from a scoped group, remove any existing label from the sa

 The system uses these label scopes: `State/`, `Priority/`, `MoSCoW/`, `Type/`, plus special labels (`Blocked`, `Duplicate`, `Automation Tracking`, `needs feedback`). All labels exist at the organization level and are pre-configured during project bootstrapping.

-## **CRITICAL** Rules
+## Rules

 1. **NEVER create labels.** You can only apply existing organization-level labels.
 2. **Validate before applying.** Use the curl command to confirm the label exists before trying to apply it.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#6B7280"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -52,6 +48,6 @@ Supervisor: <supervisor_name> | Agent: <agent_name>

 The signature is always preceded by a horizontal rule (`---`) and appears at the very end of the content.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* this agent makes no direct paginated list calls, but any future tool or REST calls returning arrays must be paginated.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#10B981"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -91,7 +87,7 @@ git -C "$WORK_DIR" push --force-with-lease origin "$BRANCH"

 Never use `--force` without `--lease`.

-## **CRITICAL** Rules
+## Rules

 1. **Always use --force-with-lease, never --force.** This prevents overwriting others' work.
 2. **Abort on rebase conflicts.** Report them; don't try to resolve automatically.
@@ -8,10 +8,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: secondary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -54,7 +50,7 @@ git -C "$WORK_DIR" push origin "$BRANCH"

 If no changes are staged, report that to the caller instead of creating an empty commit.

-## **CRITICAL** Rules
+## Rules

 1. **Never create empty commits.**
 2. **Always verify with `git status` before committing.**
@@ -10,10 +10,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: "#95A5A6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -114,7 +110,7 @@ Each cycle:
 - Prefix: `AUTO-GROOMER`
 - Cycle interval: ~5 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Paginate everything.** Always fetch all pages of issues and PRs.
 2. **Re-check before dispatching.** Don't rely on stale lists — always re-check the current state right before choosing the next item to groom.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -85,9 +81,9 @@ Your prompt includes:
 6. Identify the linked issue (from closing keywords like `Closes #N` in the PR body).
 7. Fetch the linked issue's details and labels.

-## Step 2: Run the following Quality Analysis
+## Step 2: Run the 10-Point Quality Analysis

-Perform ALL the following checks on the item:
+Perform ALL 10 checks on the item:

 ### 1. Duplicate Detection
 Check if this issue/PR describes the same work as another open item. Search for issues with similar titles or descriptions. If a duplicate is found, close this one with a comment linking to the original, or close the other if this one is more complete.
@@ -134,8 +130,6 @@ Also verify the PR has the following, and if it doesnt add it:
 - A closing keyword (`Closes #N` or `Fixes #N`) in its description
 - A dependency link (PR blocks the linked issue)

-Finally if a PR has been merged or closed be sure to update its associated issue if needed. In particular update linked issues and the PR itself to `State/Completed` via `forgejo-label-manager`.
-
 ### 11: PR-Specific: Address any relevant remarks from reviews

 Check formal reviews as well as informal comments left as reviews. Any concerns raised about the PR or its linked ticket, not related to the source code itself (for example labels, the PR description, milestone setting, etc) should be addressed.
@@ -163,7 +157,7 @@ Fixes applied:
 - Applied Priority/Medium label (was missing)
 ```

-## **CRITICAL** Rules
+## Rules

 1. **One item, then exit.** Analyze the single issue or PR you were given. Do not scan other items.
 2. **Read all comments and reviews.** For PRs, the formal reviews and review comments are essential context — they may explain why labels or states are in a particular condition.
@@ -9,10 +9,6 @@ temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 color: "#3498DB"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -113,7 +109,7 @@ When human feedback changes the nature of a ticket (e.g., a comment reveals the
 - Prefix: `AUTO-LIAISON`
 - Cycle interval: ~2 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Professional communication.** Follow CODE_OF_CONDUCT.md. No emojis. Respectful tone.
 2. **Respond promptly.** Humans expect fast responses. Your 2-minute polling ensures this.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -60,7 +56,7 @@ Your prompt describes the specific task: triage a new issue, respond to a human
 4. When feedback changes ticket nature: update the description, post a diff comment, tag the user.
 5. Exit.

-## **CRITICAL** Rules
+## Rules

 1. **One task, then exit.**
 2. **Professional communication.** Follow CODE_OF_CONDUCT.md. No emojis.
@@ -9,10 +9,6 @@ mode: all
 temperature: 0.1
 color: primary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -65,11 +61,11 @@ Pass the relevant briefing content (especially CONTRIBUTING.md rules for commits

 ## PR-First Priority

-This is your most important rule. You must dispatch workers to ALL open PRs before dispatching any new issue workers. The sequence every cycle is:
+This is your most important rule. You must dispatch workers to ALL open bot PRs before dispatching any new issue workers. The sequence every cycle is:

 1. Fetch all open PRs (paginate through every page — Forgejo returns at most 50 per page)
 2. Filter to PRs that either have failing CI quality gates/tests or has a active review with requested changes (not approved)
-3. Dispatch a worker for every PR that doesn't already have an active worker/
+3. Dispatch a worker for every bot PR that doesn't already have an active worker/
 4. Only after every open PR is covered may you fill remaining slots with issue workers

 ## Workers
@@ -78,7 +74,7 @@ Workers are `implementation-worker` agents, launched through **tier selectors**

 ### Tier Selectors

-The `implementation-worker` agent has no model set — it inherits the model from its caller. To control the model tier, you do NOT launch `implementation-worker` directly. Instead, you launch the appropriate **tier selector agent** via `async-agent-manager` agent:
+The implementation-worker agent has no model set — it inherits the model from its caller. To control the model tier, you do NOT launch `implementation-worker` directly. Instead, you launch the appropriate **tier selector agent** via async-agent-manager:

 | Tier | Agent to Launch | Model |
 |---|---|---|
@@ -87,7 +83,7 @@ The `implementation-worker` agent has no model set — it inherits the model fro
 | 3 | `tier-sonnet` | Sonnet |
 | 4 | `tier-opus` | Opus (most expensive) |

-When you tell `async-agent-manager` agent to launch `tier-codex`, for example, the session runs at the Codex model. The tier selector's prompt should say "invoke implementation-worker" followed by the full task details. The tier selector invokes implementation-worker as a subagent, which inherits the Codex model.
+When you tell async-agent-manager to launch `tier-codex`, for example, the session runs at the Codex model. The tier selector's prompt should say "invoke implementation-worker" followed by the full task details. The tier selector invokes implementation-worker as a subagent, which inherits the Codex model.

 ### Worker Tags

@@ -101,7 +97,7 @@ These tags prevent duplicate dispatch — before assigning work, search for an e
 Launch workers via the `async-agent-manager` subagent. For each worker:

 1. Determine the appropriate tier (see Progressive Escalation below).
-2. Tell `async-agent-manager` agent to launch the corresponding tier selector agent (e.g., `tier-haiku` for Tier 1).
+2. Tell async-agent-manager to launch the corresponding tier selector agent (e.g., `tier-haiku` for Tier 1).
 3. The tier selector's prompt must say "invoke implementation-worker" followed by:
   - Whether this is a PR fix or new issue implementation
   - The PR number or issue number
@@ -120,7 +116,7 @@ These comments are how you track escalation state across worker sessions.

 ### Monitoring Workers

-Every cycle, search for your workers using `async-agent-manager` by tag pattern (`[AUTO-IMP-ISSUE-*]` and `[AUTO-IMP-PR-*]`). Count active workers, verify they're progressing (by reviewing their session messages via `async-agent-manager`), and note any that have completed or errored. Workers completing is normal — they finished their task. Restart any errors workers via `async-agent-manager`.
+Every cycle, search for your workers by tag pattern (`[AUTO-IMP-ISSUE-*]` and `[AUTO-IMP-PR-*]`). Count active workers, verify they're progressing, and note any that have completed or errored. Workers completing is normal — they finished their task.

 ## Progressive Escalation

@@ -175,11 +171,7 @@ Always paginate Forgejo API results. Never pass a `limit` that caps results belo
 - Cycle interval: ~2 minutes
 - Create announcements for: human escalations, zero available work, capacity alerts

-At startup, and then approximately every 10 minutes there after (the update interval) you need to update your automation tracking status issue by calling `automation-tracking-manager` subagent's `CREATE_TRACKING_ISSUE` operation which is used for both creating and updating the status ticket. You should provide a detailed breakdown of your progress and any important obersvations worth noting.
-
-Also anytime the status ticket is updated you should consider if you have anything important to announce to other agents, such as any state that blocks your operation that you cant resolve yourself. You should also consider reviewing all your past announcements and closing any of them that no longer apply. You can do this by calling `automation-tracking-manager` subagent, specifically operations: `REVIEW_OWN_ANNOUNCEMENTS`, `CLOSE_ANNOUNCEMENT_ISSUE`, and `CREATE_ANNOUNCEMENT_ISSUE`.
-
-## **CRITICAL** Rules
+## Rules

 1. **PRs before issues.** No exceptions. No rationalizations.
 2. **No duplicate workers.** Check for existing worker sessions by tag before dispatching.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -64,6 +60,6 @@ You review completed implementation work for correctness. You are read-only —
 - **APPROVE** — implementation is correct and complete
 - **REJECT** — with specific concerns and what needs to change

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* bash `find` or `grep` commands listing source files or test files must process all results — missing a file means an incomplete review; any future REST/curl calls returning JSON arrays must be paginated.
@@ -9,10 +9,6 @@ hidden: true
 temperature: 0.1
 # No model specified — tier is set by the supervisor via tier selectors
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -130,7 +126,7 @@ nox -e coverage_report  # Full coverage report

 When fixing a failing PR:

-1. **Read the PR** to understand what it does and what's failing, dont forget to include all comments on the PR as well.
+1. **Read the PR** to understand what it does and what's failing.

 2. **Fetch CI logs** using `ci-log-fetcher` to understand the specific failures.

@@ -188,7 +184,7 @@ You never merge PRs yourself. You create PRs and push fixes — the PR merge sup

 Always work in an isolated clone at `/tmp/<agent-type>-<instance-id>-<timestamp>/`. Never work in `/app`. Push results to remote and delete the clone before exiting.

-## **CRITICAL** Rules
+## Rules

 1. **One task, then exit.** Do not loop. Do not sleep. Do not look for more work.
 2. **Follow CONTRIBUTING.md exactly.** Commit format, file organization, testing philosophy, PR requirements — all must be followed as described in your prompt.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -91,7 +87,7 @@ When fixing a bug, check for tests tagged with `@tdd_issue_<N>` and `@tdd_expect
 3. Focus ONLY on writing code — testing and quality gates are handled by separate agents.
 4. Return a summary of what you changed and why.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.** Always work in the provided `/tmp/` working directory.
 2. **One subtask, then exit.** Do not look for more work.
@@ -8,10 +8,6 @@ temperature: 0.2
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -58,7 +54,7 @@ You run Robot Framework integration tests and fix any failures. You work in an i
 4. Re-run until all tests pass.
 5. Return a summary of results and any fixes applied.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.**
 2. **No mocking.** Integration tests exercise real dependencies.
@@ -9,10 +9,6 @@ temperature: 0.0
 model: anthropic/claude-haiku-4-5
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -63,6 +59,6 @@ A structured analysis containing:
 - **Dependencies** (blocks/blocked by)
 - **Comments summary** (especially any bot attempt comments with tier info)

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_issue_comments` (paginate ALL pages — escalation history and acceptance criteria refinements may appear in later comments and must not be missed).
@@ -8,10 +8,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#8B5CF6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -51,6 +47,6 @@ Every formatted comment ends with the bot signature block:
 Supervisor: <caller's supervisor> | Agent: <caller's agent>
 ```

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* this agent makes no direct paginated list calls, but any future tool or REST calls returning arrays must be paginated.
@@ -8,10 +8,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -54,6 +50,6 @@ You query the Forgejo issue tracker and return a prioritized list of issues matc

 A prioritized list of matching issues, sorted by: milestone order (lowest first), then priority label (Critical > High > Medium > Low > Backlog), then issue number.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_issues` (default 20 — this agent’s primary function; must use `limit=50` and paginate ALL pages or the returned list is silently truncated and callers act on incomplete data); `forgejo_list_repo_milestones` (paginate to correctly map milestone ordering for priority sorting).
@@ -8,10 +8,6 @@ temperature: 0.3
 model: anthropic/claude-haiku-4-5
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -44,7 +40,7 @@ You post implementation notes as comments on Forgejo issues. Your caller provide

 Notes should document: design decisions, discoveries during implementation, assumptions made, code locations affected, test results, and any deviations from the original plan.

-## **CRITICAL** Rules
+## Rules

 1. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 2. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* this agent makes no direct paginated list calls, but any future tool or REST calls returning arrays must be paginated.
@@ -8,10 +8,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: "#9B59B6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -60,7 +56,7 @@ Any state → State/Wont Do
 3. If transitioning to `State/Paused`, verify the `Blocked` label is present and a blocking issue is linked. If not, refuse.
 4. Use `forgejo-label-manager` to remove the old State label and apply the new one.

-## **CRITICAL** Rules
+## Rules

 1. **Never skip states** unless going to `State/Wont Do` (which is valid from any state).
 2. **Paused requires Blocked.** Refuse to pause without the `Blocked` label and a linked blocker.
@@ -8,10 +8,6 @@ temperature: 0.1
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -60,7 +56,7 @@ You run the linter and fix all errors. You work in an isolated clone directory.

 Never run linters directly — always use `nox -e lint`.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.**
 2. **Fix all errors.** Do not exit with remaining lint failures.
@@ -9,10 +9,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -67,7 +63,7 @@ You perform a holistic review of a completed milestone. You check for integratio

 For each problem found, create an issue using `new-issue-creator` and post a summary comment on the milestone.

-## **CRITICAL** Rules
+## Rules

 1. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 2. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_issues` (use `limit=50` and paginate ALL pages — missing any issue in the milestone review means an incomplete assessment); `forgejo_list_repo_milestones` (paginate to confirm which milestone is being reviewed and which are complete).
@@ -9,10 +9,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: "#9B59B6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -73,7 +69,7 @@ Every issue must have:
 3. Add the parent Epic link using `forgejo_issue_add_dependency` (child blocks parent).
 4. Return the created issue number.

-## **CRITICAL** Rules
+## Rules

 1. **Follow the format exactly.** Every section listed above must be present.
 2. **Check for duplicates first.** Search existing issues before creating.
@@ -7,7 +7,6 @@ mode: all
 temperature: 0.3
 color: info
 permission:
-  "doom_loop": deny
  edit: deny
  webfetch: allow
  bash:
@@ -55,6 +54,6 @@ You create implementation plans. Before planning, read CONTRIBUTING.md, the prod

 Plans must account for: file organization rules, testing requirements (Behave + Robot), commit standards, PR requirements, and quality gates.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_issues` (use `limit=50` and paginate all pages to understand the full scope of existing work before planning); `forgejo_list_repo_milestones` (paginate to see all milestones for timeline planning); `forgejo_list_repo_pull_requests` (paginate to see all in-flight work).
@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -79,7 +75,7 @@ git -C "$WORK_DIR" push --force-with-lease origin "$BRANCH"

 5. If the fix doesn't resolve all failures, repeat from step 1.

-## **CRITICAL** Rules
+## Rules

 1. **Never use --force without --lease.**
 2. **Always run quality gates locally before pushing.**
@@ -9,10 +9,6 @@ temperature: 0.0
 model: anthropic/claude-sonnet-4-6
 color: "#9B59B6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -72,7 +68,7 @@ You create a pull request on Forgejo with all required metadata per CONTRIBUTING
 6. Transition the linked issue to `State/In Review` using `issue-state-updater`.
 7. Return the PR number.

-## **CRITICAL** Rules
+## Rules

 1. **Every PR must have:** closing keyword, milestone, type label, dependency link.
 2. **Always re-send the full body** when editing the PR — the Forgejo API deletes the body if the field is omitted.
@@ -8,10 +8,6 @@ temperature: 0.3
 model: anthropic/claude-haiku-4-5
 color: secondary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -73,6 +69,6 @@ Agent: pr-description-writer

 The `Closes #N` keyword is MANDATORY — it auto-closes the linked issue on merge.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* this agent makes no direct paginated list calls, but any future tool or REST calls returning arrays must be paginated.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: "#10B981"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -65,7 +61,7 @@ When calling `forgejo_edit_pull_request`, you MUST always include the current `b
 - **Dependencies** — via `forgejo_issue_add_dependency` / `forgejo_issue_remove_dependency`
 - **Title** — via `forgejo_edit_pull_request`

-## **CRITICAL** Rules
+## Rules

 1. **Always re-send the full body.** This is the most important rule.
 2. **Validate CONTRIBUTING.md compliance.** Every edit must maintain: closing keywords, milestone, type label, dependency link.
@@ -8,10 +8,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: "#6366F1"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -57,7 +53,7 @@ You are the unified interface for pull request operations. You delegate to speci

 You ensure all PR operations follow CONTRIBUTING.md requirements (closing keywords, milestone, type label, dependency links).

-## **CRITICAL** Rules
+## Rules

 1. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 2. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_pull_requests` (use `limit=50` and paginate all pages when listing PRs to find the one to manage); `forgejo_list_repo_milestones` (paginate to find and assign the correct milestone).
@@ -10,10 +10,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: "#059669"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -37,7 +33,6 @@ permission:
    "automation-tracking-manager": allow
    "repo-isolator": allow
    "git-commit-helper": allow
-    "forgejo-label-manager": allow
  "forgejo_*": deny
  "forgejo_list_repo_pull_requests": allow
  "forgejo_get_pull_request_by_index": allow
@@ -70,6 +65,60 @@ Your prompt from the product-builder includes:
 - Repository owner/name, Forgejo PAT, git identity
 - A customized briefing containing CONTRIBUTING.md merge requirements and open announcements

+## CRITICAL: Triage Strategy — Speed Over Perfection
+
+**Do NOT spend time pre-filtering or serially checking reviews before dispatching workers.** The correct approach is:
+
+1. **Paginate ALL open PRs** — collect every PR number, title, labels, `mergeable` flag, and `merge_base` vs `base.sha`.
+2. **Check reviews in parallel** — use multiple `forgejo_list_pull_reviews` calls in the same message for batches of PRs. Do not check them one at a time sequentially.
+3. **Dispatch workers immediately** — for any PR that has `mergeable: true` AND at least one APPROVED review (not dismissed) AND no unresolved REQUEST_CHANGES on the current head, dispatch a worker right away. Do not wait to finish checking all other PRs first.
+4. **Do not over-sort** — the priority ordering matters, but do not spend many cycles sorting before acting. Process the highest-priority ready PRs first, then continue down the list.
+
+**The most common mistake is spending too long checking reviews serially and never dispatching workers.** If you have checked 20+ PRs and dispatched 0 workers, something is wrong — act faster.
+
+## Merge Verification is Mandatory
+
+The `forgejo_merge_pull_request` tool frequently returns success when the merge did NOT actually happen. Forgejo silently rejects merges when a branch is behind. You must verify every merge:
+
+```pseudocode
+PROCEDURE MERGE_PR(pr_number):
+  -- Step 1: Check staleness
+  pr := forgejo_get_pull_request_by_index(pr_number)
+  IF pr.merge_base != pr.base.sha:
+    -- Branch is behind; call worker as blocking subagent to rebase, wait for CI, and merge
+    CALL_BLOCKING_WORKER(pr_number)  -- blocks until worker finishes
+    RETURN "rebase_handled"
+
+  -- Step 2: Attempt merge
+  forgejo_merge_pull_request(pr_number, style="rebase")
+
+  -- Step 3: Verify merge actually happened
+  pr := forgejo_get_pull_request_by_index(pr_number)
+  IF pr.merged == true AND pr.state == "closed":
+    post_comment(pr_number, "Automatically merged (verified)")
+    update_linked_issues_to_completed(pr_number)
+    RETURN "merged"
+  ELSE:
+    -- Merge silently failed — dispatch worker to handle
+    CALL_BLOCKING_WORKER(pr_number)
+    RETURN "worker_handled"
+```
+
+## Merge Criteria
+
+Before merging any PR, ALL of the following must be true:
+
+1. **Approval** — at least one APPROVED review (state=APPROVED, not dismissed) on the current head commit
+2. **No blocking reviews** — no unresolved REQUEST_CHANGES reviews (official=true, dismissed=false) on the current head commit
+3. **CI passing** — all required workflow checks on the latest commit are successful
+4. **No conflicts** — `mergeable: true` (Forgejo reports no merge conflicts)
+5. **No `Needs Feedback` label** — the PR is not waiting for human input
+6. **No `Blocked` label** — the PR is not explicitly blocked
+
+**Staleness (`merge_base != base.sha`) is NOT a hard blocker for dispatching a worker.** A worker can rebase a stale PR. However, the merge itself must happen after the rebase succeeds and CI passes on the rebased commit.
+
+**Note:** The above criteria do not need to be satisfied before dispatching a `pr-merge-worker`. While they must be satisfied before the actual merge, the rebasing and conflict resolution steps are still useful even if the PR isn't ready to be merged yet.
+
 ## Workers

 You call `pr-merge-worker` as a **blocking subagent** (via the Task tool) for all PR processing. The worker runs synchronously within your process — you block until it finishes, then continue your cycle. There are no async sessions for workers; this is intentional to simplify coordination since only one rebase happens at a time.
@@ -84,50 +133,55 @@ Every worker prompt must include:

 ## Main Loop

-Before starting the main loop below be sure to create your status tracking ticket (see the tracking section below).
+Poll every 5 minutes using `bash("sleep 300", timeout=360000)`.

-In an infinite loop do the following each cycle:
+Each cycle:

-1. **Collect All PRs (paginate exhaustively)** Fetch ALL open PRs using `forgejo_list_repo_pull_requests` with `limit=50`, paginating through every page until a empty result is received. Record for each PR: number, title, labels, `mergeable`, `merge_base`, `base.sha`, head SHA.
-2. Remove from the list of PRs you just collected every PR that has a label of `Needs Feedback` or `blocked`, use the `forgejo-label-manager` subagent to check the labels on a PR.
-3. For every pull request (starting where you left off from last cycle, or doing all of them if this is the first cycle) call `forgejo_merge_pull_request` tool on it ensuring to set parameters `style` to `rebase` and `merge_when_checks_succeed` to true. Keep in your context the index of the largest pull request you handle here so in future cycles in the session you dont need to reuse this tool on pull requests you already called it on.
-4. Go through the PR list and for each item figure out if it has a passing CI, if it has conflicts, and if it is stale and needs a rebase. Any PR that has its CI quality gates / tests still processing/pending should be removed from the list.
-5. Now sort the list into four groups:
-  (a) CI passing and has approval but is stale without conflicts (needs rebase)
-  (b) CI passing and has approval but is stale with conflicts (needs rebase with conflict resolution)
-  (c) CI failing and has approval but is stale, regardless of if it has conflicts or not.
-  (d) everything else. 
-6. Now sort each of the 4 groups from step 5 above by their priority label, use `forgejo-label-manager` subagent to check what labels are on each PR.
-7. If group (a) from step 5 is empty, then skip this step, if it has one or more PR in it then sequentially dispatch a single `pr-merge-worker` subagent for each PR in the group and then start the cycle over at #1 (skipping the rest of the steps in this cycle)
-8. If group (b) from step 5 is empty, then skip this step, if it has one or more PR in it then sequentially dispatch a single `pr-merge-worker` subagent for each PR in the group and then start the cycle over at #1 (skipping the rest of the steps in this cycle)
-9. If group (c) from step 5 is empty, then skip this step, if it has one or more PR in it then sequentially dispatch a single `pr-merge-worker` subagent for each PR in the group and then start the cycle over at #1 (skipping the rest of the steps in this cycle)
-10. If group (d) from step 5 is empty, then skip this step, if it has one or more PR in it then sequentially dispatch a single `pr-merge-worker` subagent for each PR in the group and then start the cycle over at #1 (skipping the rest of the steps in this cycle)
-11. Sleep for 5 minutes using `bash("sleep 300", timeout=360000)`.
-12. If at least 10 minutes has passed since the last time you updated your automation tracking status ticket, or if you never created/updated one, (see tracking section below) then update your tracking ticket using the `automation-tracking-manager` subagent according to the details provided in the section labeled "tracking" below.
-13. Loop through the cycle indefinately by starting at step 1 above again.
+### Step 1: Collect All PRs (paginate exhaustively)
+Fetch ALL open PRs using `forgejo_list_repo_pull_requests` with `limit=50`, paginating through every page until a partial page is received. Record for each PR: number, title, labels, `mergeable`, `merge_base`, `base.sha`, head SHA.
+
+### Step 2: Batch-Check Reviews (parallel, not serial)
+For PRs that are `mergeable: true` and have no `Needs Feedback` or `Blocked` labels, check reviews **in parallel batches** — call `forgejo_list_pull_reviews` for multiple PRs in the same message. Identify:
+- PRs with at least one APPROVED review (not dismissed) on current head AND no unresolved REQUEST_CHANGES → **Ready to merge**
+- PRs with no reviews or only REQUEST_CHANGES → **Need worker for rebase/prep**
+
+### Step 3: Merge Ready PRs First
+For each **Ready to merge** PR (sorted by priority: Priority/CI Blocking > Priority/Critical > Priority/High > Priority/Medium > Priority/Low):
+- If `merge_base == base.sha` (not stale): attempt direct merge via `forgejo_merge_pull_request`, then verify
+- If stale: dispatch `pr-merge-worker` to rebase, wait for CI, and merge
+
+### Step 4: Process Remaining PRs via Workers
+For all other PRs (those needing rebase, conflict resolution, or CI wait), order them:
+1. CI passes + has approval (but stale/conflicted)
+2. CI failing without conflicts + has approval
+3. CI failing with conflicts + has approval
+4. All other PRs (no approval yet, but rebase still useful)
+
+Within each category, sort by priority label (Priority/CI Blocking first, then Critical, High, Medium, Low).
+
+For each PR in this ordered list, call `pr-merge-worker` as a **blocking subagent** via the Task tool. Block until the worker finishes before processing the next PR.
+
+### Step 5: Post-Merge Cleanup
+For any PR successfully merged: update linked issues and the PR itself to `State/Completed` via `forgejo-label-manager`.

 ## Tracking

 - Prefix: `AUTO-MERGE`
- Update interval: ~10 minutes
+- Cycle interval: ~5 minutes
 - Create announcements for: merge verification failures, persistent stale PRs, PRs stuck with REQUEST_CHANGES for >24h

-At startup, and then approximately every 10 minutes there after (the update interval) you need to update your automation tracking status issue by calling `automation-tracking-manager` subagent's `CREATE_TRACKING_ISSUE` operation which is used for both creating and updating the status ticket. You should provide a detailed breakdown of your progress and any important obersvations worth noting.
-
-Also anytime the status ticket is updated you should consider if you have anything important to announce to other agents, such as any state that blocks your operation that you cant resolve yourself. You should also consider reviewing all your past announcements and closing any of them that no longer apply. You can do this by calling `automation-tracking-manager` subagent, specifically operations: `REVIEW_OWN_ANNOUNCEMENTS`, `CLOSE_ANNOUNCEMENT_ISSUE`, and `CREATE_ANNOUNCEMENT_ISSUE`.
-
-
-## **CRITICAL** Rules
+## Rules

 1. **Always verify merges.** Never trust the merge API response alone. Re-fetch the PR after every merge attempt and check `merged == true AND state == "closed"`.
 2. **Never merge immediately after rebase.** Wait for CI to complete quality gates/tests first.
 3. **Pass credentials down.** Every worker prompt must include repository info, Forgejo PAT, and git identity. Workers never read environment variables.
-4. **Bot signature on all Forgejo content:**
+4. **Batch review checks.** Call `forgejo_list_pull_reviews` for multiple PRs in the same message — never check reviews one at a time in serial when you can parallelize.
+5. **Act fast on ready PRs.** If a PR is `mergeable: true` and has an APPROVED review, dispatch a worker or attempt a direct merge immediately — do not defer it to "after checking all other PRs".
+6. **Bot signature on all Forgejo content:**
 ```
 ---
 **Automated by CleverAgents Bot**
 Supervisor: PR Merge Pool | Agent: pr-merge-pool-supervisor
 ```
-5. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
-6. **Exhaustive pagination for all list results.** Every tool call that returns a list must be treated as potentially paginated. Always set `limit=50` for Forgejo MCP tools. After each list response, check whether the number of returned items equals the page size — if so, fetch the next page. Never assume the first response is the complete result. This applies to: `forgejo_list_repo_pull_requests` (must paginate ALL pages — missing a page means a ready PR never gets merged), `forgejo_list_pull_reviews` (paginate to see all review rounds), `forgejo_list_issue_comments` (paginate when updating linked issues post-merge).
-7. **Never close or change the label of a PR's issue** The issue for a PR will automatically be closed and the grooming agent will update its labels. Never close the originating issue directly or change its state.
+7. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
+8. **Exhaustive pagination for all list results.** Every tool call that returns a list must be treated as potentially paginated. Always set `limit=50` for Forgejo MCP tools. After each list response, check whether the number of returned items equals the page size — if so, fetch the next page. Never assume the first response is the complete result. This applies to: `forgejo_list_repo_pull_requests` (must paginate ALL pages — missing a page means a ready PR never gets merged), `forgejo_list_pull_reviews` (paginate to see all review rounds), `forgejo_list_issue_comments` (paginate when updating linked issues post-merge).
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -35,9 +31,7 @@ permission:
    "*": deny
    "repo-isolator": allow
    "git-commit-helper": allow
-    "forgejo-label-manager": allow
  "forgejo_*": deny
-  "forgejo_merge_pull_request": allow
  # CRITICAL: Never list repo-level labels — use org labels via forgejo-label-manager
  "forgejo_list_repo_labels": deny
  # CRITICAL: Label creation is COMPLETELY FORBIDDEN
@@ -61,14 +55,14 @@ Your prompt tells you which PR to rebase. You must:
 3. Resolve any conflicts that arise by reviewing the recent git history and using that to fix the conflicts
 4. Force-push with lease using `git-commit-helper`
 5. Clean up the clone.
-6. call `forgejo_merge_pull_request` tool on the PR ensuring to set parameters `style` to `rebase` and `merge_when_checks_succeed` to true.
+6. Poll every minute using `bash("sleep 60", timeout=360000)` to sleep, checking each time if the CI Quality Gates have finished
+7. Once the quality gates finish then merge with a fast-forward or rebase merge if the PR is mergable, if not then skip the merge.
 8. Report back with any relevant details.

-## **CRITICAL** Rules
+## Rules

 1. **One task, then exit.** Do not loop. Do not sleep. Do not look for more work.
 2. **Force-push with lease only.** Never use `--force` without `--lease`.
 3. **Clean up your clone.** Delete the temporary clone directory before exiting.
 4. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 5. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `git log` listing commits during conflict resolution must be fully read; any future REST/curl calls returning JSON arrays must be paginated.
-6. **Never close or change the label of a PR's issue** The issue for a PR will automatically be closed and the grooming agent will update its labels. Never close the originating issue directly or change its state.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -30,7 +26,6 @@ permission:
    "*": deny
    "async-agent-manager": allow
    "automation-tracking-manager": allow
-    "forgejo-label-manager": allow
  "forgejo_*": deny
  "forgejo_list_repo_pull_requests": allow
  "forgejo_get_pull_request_by_index": allow
@@ -81,26 +76,19 @@ Launch workers via the `async-agent-manager`. Each worker's prompt must include:

 ## Main Loop

-Before starting the main loop below be sure to create your status tracking ticket (see the tracking section below). Be careful while running the loop below that you keep track of the total number of active workers, and
+Poll every 3 minutes using `bash("sleep 180", timeout=240000)`.

-In an infinite loop do the following each cycle:
+Each cycle:

-1. **Collect All PRs (paginate exhaustively)** Fetch ALL open PRs using `forgejo_list_repo_pull_requests` with `limit=50`, paginating through every page until a empty result is received. Record for each PR: number, title, labels, `mergeable`, `merge_base`, `base.sha`, head SHA.
-2. Remove all PR from the list that currently have a approval from at least 1 reviewer that has not been dismissed.
-3. Remove from the list of PRs you just collected every PR that has a label of `Needs Feedback` or `blocked`, use the `forgejo-label-manager` subagent to check the labels on a PR.
-4. Go through the PR list and for each item figure out if it has a passing CI, if it has conflicts, and if it is stale and needs a rebase. Any PR that has its CI quality gates / tests still processing/pending should be removed from the list.
-5. Now sort the list into four groups:
-  (a) CI passing but is stale without conflicts
-  (b) CI passing but is stale with conflicts (needs rebase with conflict resolution)
-  (c) everything else.
-6. Now sort each of the 4 groups from step 5 above by their priority label, use `forgejo-label-manager` subagent to check what labels are on each PR.
-7. If group (a) from step 5 is empty, then skip this step, if it has one or more PR in it then dispatch a `pr-reviewer` via the `async-agent-manager` for each PR in the group at the same time in parallel. Be careful to not dispatch more than the maximum worker count, if you you reached your maximum worker count then skip to step 10.
-8. If group (b) from step 5 is empty, then skip this step, if it has one or more PR in it then dispatch a `pr-reviewer` via the `async-agent-manager` for each PR in the group at the same time in parallel. Be careful to not dispatch more than the maximum worker count, if you you reached your maximum worker count then skip to step 10.
-9. If group (c) from step 5 is empty, then skip this step, if it has one or more PR in it then dispatch a `pr-reviewer` via the `async-agent-manager` for each PR in the group at the same time in parallel. Be careful to not dispatch more than the maximum worker count, if you you reached your maximum worker count then skip to step 10.
-10. Sleep for 3 minutes using `bash("sleep 180", timeout=360000)`.
-11. If at least 10 minutes has passed since the last time you updated your automation tracking status ticket, or if you never created/updated one, (see tracking section below) then update your tracking ticket using the `automation-tracking-manager` subagent according to the details provided in the section labeled "tracking" below.
-12. Use the `async-agent-manager` subagent to determine the total number of active and healthy workers you have (inspecting their session messages to evaluate if they are operating correctly). Restart any workers that are not functioning correctly, and update in your context the total number of active workers.  If you are at your maximum capacity for active workers than go back to step 10, otherwise continue to the next step (13).
-13. Loop through the cycle indefinately by starting at step 1 above again.
+1. **Discover PRs needing review.** List all open PRs. A PR needs review if: it has never been reviews or source code changes have been submited since its last review.
+
+2. **Skip already-covered PRs.** Check for existing worker sessions by tag before dispatching.
+
+3. **Dispatch reviewers.** Fill available worker slots with PRs needing review.  Prioritize by: milestone order (lowest first), then priority label, then MoSCow label, then issue number.
+
+4. **Monitor workers.** Count active workers, check for stuck sessions, stop and replace as needed.
+
+5. **Update tracking.** Every 5 cycles, create a status tracking issue via `automation-tracking-manager` with prefix `AUTO-REV-POOL`.

 ## Tracking

@@ -108,15 +96,12 @@ In an infinite loop do the following each cycle:
 - Cycle interval: ~3 minutes
 - Create announcements for: review backlog growing faster than workers can handle

-At startup, and then approximately every 10 minutes there after (the update interval) you need to update your automation tracking status issue by calling `automation-tracking-manager` subagent's `CREATE_TRACKING_ISSUE` operation which is used for both creating and updating the status ticket. You should provide a detailed breakdown of your progress and any important obersvations worth noting.
+## Rules

-Also anytime the status ticket is updated you should consider if you have anything important to announce to other agents, such as any state that blocks your operation that you cant resolve yourself. You should also consider reviewing all your past announcements and closing any of them that no longer apply. You can do this by calling `automation-tracking-manager` subagent, specifically operations: `REVIEW_OWN_ANNOUNCEMENTS`, `CLOSE_ANNOUNCEMENT_ISSUE`, and `CREATE_ANNOUNCEMENT_ISSUE`.
-
-## **CRITICAL** Rules
-
-1. **Use reviewer credentials.** Workers must authenticate as the reviewer bot, not the primary bot. This allows formal approval from a different account.
-2. **No duplicate reviews.** Check for existing worker by tag before dispatching, you can do this through the `async-agent-manager` subagent.
-3. **Never review code yourself.** Dispatch workers for all reviews.
+1. **Only review bot PRs.** Human PRs are reviewed by humans. Only review PRs whose author matches the primary bot username.
+2. **Use reviewer credentials.** Workers must authenticate as the reviewer bot, not the primary bot. This allows formal approval from a different account.
+3. **No duplicate reviews.** Check for existing worker by tag before dispatching.
+4. **Never review code yourself.** Dispatch workers for all reviews.
 5. **Pass credentials down.** Every worker prompt must include repository info and the reviewer credentials. Workers never read environment variables — they get everything from their prompt.
 6. **Bot signature on all Forgejo content:**
 ```
@@ -10,10 +10,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -29,7 +25,6 @@ permission:
  task:
    "*": deny
    "ci-log-fetcher": allow
-    "forgejo-label-manager": allow
  "forgejo_*": deny
  "forgejo_get_issue_by_index": allow
  "forgejo_list_issue_comments": allow
@@ -69,17 +64,15 @@ The Forgejo MCP tools authenticate as the primary bot account (HAL9000). But rev

 ## Review Process

-1. **Fetch the PR** using `forgejo_get_pull_request_by_index` to get the PR metadata (title, description, linked issue, milestone, labels). Note: use `forgejo-label-manager` subagent to get the labels.
+1. **Fetch the PR** using `forgejo_get_pull_request_by_index` to get the PR metadata (title, description, linked issue, milestone, labels).

-2. **Read all comments on the PR** using `forgejo_list_issue_comments` (works on PR not just issues)
+2. **Get the diff** using `forgejo_get_pull_request_diff` and the list of changed files using `forgejo_list_pull_request_files`.

-3. **Get the diff** using `forgejo_get_pull_request_diff` and the list of changed files using `forgejo_list_pull_request_files`.
+3. **Read the linked issue** using `forgejo_get_issue_by_index` to understand what the PR is supposed to accomplish (acceptance criteria, subtasks, definition of done).

-4. **Read the linked issue** using `forgejo_get_issue_by_index` to understand what the PR is supposed to accomplish (acceptance criteria, subtasks, definition of done).
+4. **Check CI status** using `ci-log-fetcher` if CI has run on the latest commit.

-5. **Check CI status** using `ci-log-fetcher` if CI has run on the latest commit.
-
-6. **Review the code** against these criteria:
+5. **Review the code** against these criteria:
   - **Correctness**: Does the code do what the linked issue describes?
   - **Spec alignment**: Does it match the product specification?
   - **CONTRIBUTING.md compliance**: Commit format, file organization, testing, type safety
@@ -130,7 +123,21 @@ curl -s -X POST \
  }'
 ```

-## **CRITICAL** Rules
+## Dynamic Review Focus
+
+Each review should emphasize different aspects to catch a wider range of issues. Vary your focus based on the PR number (use `PR_NUMBER % 5` to rotate):
+
+| PR mod 5 | Primary Focus |
+|---|---|
+| 0 | Correctness and spec alignment |
+| 1 | Test quality and coverage |
+| 2 | Error handling and edge cases |
+| 3 | Performance and resource management |
+| 4 | API consistency and naming |
+
+Always check all criteria, but spend extra attention on the primary focus area.
+
+## Rules

 1. **One PR, then exit.** Do not loop or sleep.
 2. **Use reviewer credentials for all writes.** Never post reviews as the primary bot.
@@ -8,10 +8,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#3B82F6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -59,6 +55,6 @@ You analyze a PR's status across all dimensions and return a structured report.
 - **Linked issue status** — issue state, milestone, dependencies
 - **Overall assessment** — ready to merge, needs work, or blocked

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_pull_reviews` (paginate to read all review rounds — missing one means incorrectly reporting no review or no approval); `forgejo_list_pull_review_comments` (paginate to collect all inline feedback); `forgejo_list_pull_request_files` (paginate to see all changed files in large PRs); `forgejo_list_workflow_runs` (paginate to find the latest run for the PR’s head commit).
@@ -8,10 +8,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: primary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -273,7 +269,7 @@ Your context window fills up over time from monitoring output. Periodically disc

 Everything else is reconstructable from the OpenCode server API, Forgejo, and the `agent-prefix-info` / `agent-type-info` subagents.

-## **CRITICAL** Rules
+## Rules

 1. **Never do supervisor work.** You never implement, edit code, create PRs, merge PRs, or review code. If something needs doing, a supervisor does it.

@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -69,6 +65,6 @@ to verify when all other points are satisfied.
 - **COMPLETE** if all 10 checks pass
 - **INCOMPLETE** with a list of which checks failed and specific details

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_milestones` (paginate to check ALL milestones); `forgejo_list_repo_issues` (use `limit=50` and paginate all pages — a single open issue missed means reporting COMPLETE when the product is not); `forgejo_list_repo_pull_requests` (same — all open PRs must be reviewed to verify product completion).
@@ -9,10 +9,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: primary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -65,7 +61,7 @@ You set up project infrastructure from scratch. Your caller provides the product
 6. **Forgejo milestones** — initial milestones based on product vision
 7. **Branch protection** — require CI and review for master/main

-## **CRITICAL** Rules
+## Rules

 1. **Detect before creating.** Always check if something exists before creating it.
 2. **Never overwrite.** If a file or label already exists, skip it.
@@ -9,10 +9,6 @@ temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 color: "#8E44AD"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -87,7 +83,7 @@ Each cycle:
 - Prefix: `AUTO-PROJ-OWN`
 - Cycle interval: ~5 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Only project owners assign MoSCoW labels.** Per CONTRIBUTING.md, MoSCoW labels are set exclusively by the project owner. That's you.
 2. **Comment on every triage decision.** Explain why an issue was verified, rejected, or marked Wont Do.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -54,7 +50,7 @@ Your prompt describes the triage decisions to apply (e.g., "verify issue #42 as
 1. For each issue in the batch: update its state label (via `issue-state-updater`), apply MoSCoW and priority labels (via `forgejo-label-manager`), assign milestone, and post a comment explaining the triage decision.
 2. Exit.

-## **CRITICAL** Rules
+## Rules

 1. **One batch, then exit.**
 2. **Comment on every triage decision.** Explain why.
@@ -9,10 +9,6 @@ temperature: 0.0
 model: anthropic/claude-sonnet-4-6
 color: error
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -63,7 +59,7 @@ For each violation found, create an issue using `new-issue-creator` with:
 - Detailed description of what was merged without checks
 - Reference to the specific PR and commit

-## **CRITICAL** Rules
+## Rules

 1. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 2. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_pull_requests` (use `limit=50` and paginate ALL pages — checking only the first page means CI violations in older PRs go undetected); `forgejo_list_pull_reviews` (paginate to verify all reviews on each PR); `forgejo_list_workflow_runs` (paginate to find all runs and identify any PRs merged without CI); `forgejo_list_branches` (paginate to verify branch protection on all branches).
@@ -9,10 +9,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#6B7280"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -48,6 +44,6 @@ You load project reference materials and prepare them for distribution to child

 You invoke `ref-reader` to get the raw summaries, then optionally tailor the content for specific consumers based on their role.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* bash `find` commands listing reference files must process all results; any future REST/curl calls returning JSON arrays must be paginated.
@@ -9,10 +9,6 @@ temperature: 0.0
 model: google/gemini-2.5-pro
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -64,6 +60,6 @@ A structured summary covering:
 - Key architectural decisions from the specification
 - Current milestone status from the timeline

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* bash `find` commands listing documentation files must process all results to ensure the full specification and CONTRIBUTING.md are read.
@@ -9,10 +9,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: "#6B7280"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -109,7 +105,7 @@ Removes the temporary directory.
 rm -rf "$WORK_DIR"
 ```

-## **CRITICAL** Rules
+## Rules

 1. **Never clone into `/app`.** Always use `/tmp/`.
 2. **Unique directory names.** Include agent name and timestamp to avoid collisions.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -81,7 +77,7 @@ Never run `robot` directly.
 4. Fix any failures and re-run until green.
 5. Return a summary of tests written.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.** Always work in the provided `/tmp/` directory.
 2. **One subtask, then exit.**
@@ -7,10 +7,6 @@ mode: primary
 temperature: 0.0
 color: error
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -48,6 +44,6 @@ You find and stop all stale automated sessions from previous runs. Use this befo
 1. Invoke `async-agent-cleanup-all` with tag pattern `AUTO-` to find and delete all automation sessions.
 2. Report how many sessions were cleaned up.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* the session list from `async-agent-cleanup-all` must include all sessions matching the pattern — if any page is missed, stale sessions survive and create duplicate supervisors on the next run.
@@ -9,10 +9,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: secondary
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -45,7 +41,7 @@ You persist session state by creating tracking issues on Forgejo via the `automa

 This agent delegates all tracking operations to `automation-tracking-manager` for consistency with the centralized tracking system.

-## **CRITICAL** Rules
+## Rules

 1. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 2. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* this agent delegates to `automation-tracking-manager`, which itself must paginate all issue searches; ensure the tracking manager is invoked with complete parameters.
@@ -8,10 +8,6 @@ temperature: 0.0
 model: google/gemini-2.5-pro
 color: info
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -43,6 +39,6 @@ permission:

 You read `docs/specification.md` and extract sections relevant to a specific issue or module. Your caller provides the context (issue description, module name) and you return the relevant architectural details.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* bash `find` or `cat` commands reading specification files must process all content; if `docs/specification/` is a directory with multiple section files, all files must be read.
@@ -10,10 +10,6 @@ temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 color: "#9B59B6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -113,7 +109,7 @@ Every 5th idle cycle (when master hasn't changed), perform a proactive deep scan
 - Prefix: `AUTO-SPEC`
 - Cycle interval: ~15 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Never remove unimplemented spec content.** The spec is forward-looking.
 2. **Two-step proposals.** Never modify the spec without approval.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -66,7 +62,7 @@ Your prompt describes the discrepancy between spec and implementation, the propo
 6. When updating an existing PR, always re-send the full body to prevent Forgejo API description deletion.
 7. Clean up and exit.

-## **CRITICAL** Rules
+## Rules

 1. **One update, then exit.**
 2. **Never remove unimplemented spec content.**
@@ -8,10 +8,6 @@ temperature: 0.0
 model: anthropic/claude-sonnet-4-6
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -60,6 +56,6 @@ You bulk-fix state label mismatches and dependency issues across all open issues
 - Always post a comment explaining each fix
 - **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.

-## **CRITICAL** Rules
+## Rules

 1. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* `forgejo_list_repo_issues` (use `limit=50` and paginate ALL pages — this agent’s entire purpose is auditing all issues; missing a page leaves state mismatches unfixed); `forgejo_list_repo_pull_requests` (same — all PRs must be checked for linked issue state correctness).
@@ -9,10 +9,6 @@ temperature: 0.0
 model: openai/gpt-5-nano
 color: "#9B59B6"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -53,7 +49,7 @@ You check off completed subtasks in a Forgejo issue body. Your caller tells you

 Always re-send the full issue body to avoid accidentally deleting content.

-## **CRITICAL** Rules
+## Rules

 1. **Apply labels via `forgejo-label-manager`.** Never apply labels directly or using the Forgejo MCP/task. All label operations must go through `forgejo-label-manager`.
 2. **Exhaustive pagination for all list results.** Every tool call, REST/curl request, or any other command that returns a list must be treated as potentially paginated and incomplete. Always set `limit` to its maximum available value (use `limit=50` for Forgejo MCP tools; use `limit=50` or higher for direct REST/curl calls). After each list response, check whether the number of returned items equals the page size — if so, there are likely more results; fetch the next page (`page=2`, `page=3`, …) and continue until receiving a partial page. Never assume the first response is the complete result. This rule applies to every list-returning call without exception. *Examples specific to this agent (not exhaustive):* this agent makes no direct paginated list calls, but any future tool or REST calls returning arrays must be paginated.
@@ -11,10 +11,6 @@ temperature: 0.1
 model: openai/gpt-5-codex
 color: accent
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -118,7 +114,7 @@ WHILE current_tier <= 4:

 If all four tiers are exhausted with the same error, return failure with the persistent error details. The supervisor handles human escalation.

-## **CRITICAL** Rules
+## Rules

 1. **Escalate only on same problem.** Different errors = progress = stay at current tier.
 2. **Never skip quality gates.** All four must pass (lint, typecheck, unit, integration).
@@ -10,10 +10,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: "#E74C3C"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -133,7 +129,7 @@ Each cycle:
 - Cycle interval: ~5 minutes
 - Read tracking issues from ALL other supervisors (you are the most comprehensive consumer)

-## **CRITICAL** Rules
+## Rules

 1. **You are the safety net.** If all other checks fail, you catch the problem.
 2. **Never merge PRs yourself.** That's the PR merge supervisor's job. If it's not working, create an announcement.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -58,7 +54,7 @@ Your prompt describes the correction to make (e.g., "fix the state label on issu
 2. Post a comment on affected issues explaining what was corrected and why.
 3. Exit.

-## **CRITICAL** Rules
+## Rules

 1. **One correction, then exit.**
 2. **Comment on changes.** Always explain what was fixed and why.
@@ -9,10 +9,6 @@ temperature: 0.2
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 color: warning
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -69,7 +65,7 @@ If unsure, treat it as a genuine bug — err on the side of fixing code rather t
 5. Re-run until all tests pass.
 6. Return a summary of what was fixed and why.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.**
 2. **Never delete a test without replacement.** If a test is obsolete, replace it with one that tests the current behavior.
@@ -10,10 +10,6 @@ temperature: 0.2
 model: google/gemini-2.5-pro
 color: "#2ECC71"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -67,13 +63,6 @@ Workers are `test-infra-worker` agents. Each worker analyzes one area of testing

 Workers use: `[AUTO-INF-<N>]` where N is a sequential number or area identifier.

-### Dispatching Workers
-
-Launch workers via the `async-agent-manager`. Each worker's prompt must include:
- Area of focus  (one of: CI timing, coverage gaps, test architecture, flaky tests, pipeline design, test data quality, missing test levels, dependency security)
- Repository owner/name, Forgejo PAT, git identity
- A customized briefing containing CONTRIBUTING.md merge requirements and open announcements
-
 ### Eight Analysis Areas

 Workers are assigned one of these focus areas:
@@ -115,7 +104,7 @@ This is the most critical concern for this supervisor. Historically, this agent
 - Prefix: `AUTO-INF-POOL`
 - Cycle interval: ~15 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Never disable or weaken checks.** Never reduce coverage below 97%. Never remove CI steps.
 2. **Five dedup checks before every issue.** No exceptions.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 model: google/gemini-2.5-pro
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -68,7 +64,7 @@ Your prompt tells you which analysis area to focus on (one of: CI timing, covera
 4. File validated proposals using `new-issue-creator`.
 5. Clean up your clone and exit.

-## **CRITICAL** Rules
+## Rules

 1. **One area, then exit.** Do not analyze additional areas.
 2. **Never disable or weaken checks.** Only propose additions and optimizations.
@@ -7,10 +7,6 @@ hidden: true
 temperature: 0.0
 model: openai/gpt-5-codex
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -7,10 +7,6 @@ hidden: true
 temperature: 0.0
 model: anthropic/claude-haiku-4-5
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -7,10 +7,6 @@ hidden: true
 temperature: 0.0
 model: anthropic/claude-opus-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -7,10 +7,6 @@ hidden: true
 temperature: 0.0
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -9,10 +9,6 @@ temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 color: "#2ECC71"
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -89,7 +85,7 @@ Each cycle:
 - Prefix: `AUTO-TIME`
 - Cycle interval: ~60 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Update at least daily.** The timeline must be updated at minimum once per day.
 2. **Never overwrite.** Add new entries; don't remove existing ones.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.1
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -63,7 +59,7 @@ Your prompt provides the current milestone status data and the timeline file for
 5. Push and exit. (No PR needed — timeline updates go directly to master.)
 6. Clean up the isolated clone using `repo-isolator`.

-## **CRITICAL** Rules
+## Rules

 1. **One update, then exit.**
 2. **Never overwrite.** Add new entries; don't remove existing ones.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.1
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -58,7 +54,7 @@ You run the type checker and fix all type errors. You work in an isolated clone
 4. Repeat until all type checks pass.
 5. Return a summary of what was fixed.

-## **CRITICAL** Rules
+## Rules

 1. **Never use `# type: ignore`.** Fix the actual type problem. This is non-negotiable per CONTRIBUTING.md.
 2. **Never work in `/app`.**
@@ -10,10 +10,6 @@ temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 color: success
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -107,7 +103,7 @@ Only assign critical bugs (`Priority/Critical`) to the active milestone. All oth
 - Prefix: `AUTO-UAT-POOL`
 - Cycle interval: ~10 minutes

-## **CRITICAL** Rules
+## Rules

 1. **Test against the spec.** The specification is the source of truth for expected behavior.
 2. **Check before filing.** Always verify no open PR already addresses a gap before creating a bug issue.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.3
 model: anthropic/claude-sonnet-4-6
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit: deny
  webfetch: deny
  bash:
@@ -67,7 +63,7 @@ Your prompt tells you which feature area to test and provides the relevant speci

 Only assign `Priority/Critical` bugs to the active milestone. All other bugs go to the backlog with no milestone.

-## **CRITICAL** Rules
+## Rules

 1. **One feature area, then exit.** Do not test additional features.
 2. **Check before filing.** Search for existing issues and PRs before creating bug reports.
@@ -8,10 +8,6 @@ hidden: true
 temperature: 0.2
 # NO MODEL SPECIFIED - inherits from caller (tier selector)
 permission:
-  "*": deny
-  "doom_loop": deny
-  question: deny
-  "sequential-thinking*": allow
  edit:
    "*": deny
    "/tmp/**": allow
@@ -58,7 +54,7 @@ You run Behave unit tests and fix any failures. You work in an isolated clone di
 4. Re-run until all tests pass.
 5. Return a summary of results and any fixes applied.

-## **CRITICAL** Rules
+## Rules

 1. **Never work in `/app`.**
 2. **Never suppress failures.** Fix the root cause.
@@ -17,6 +17,7 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).

 ### Added

+- **Developer Setup Guide** (#9123): Added comprehensive developer setup guide at `docs/development/setup.md` covering prerequisites, development workflow, testing, linting, and commit guidelines.
 - **TDD Issue-Capture Test Activation** (#7025): Replaced 234 bare `@skip` tags
  across 82 Behave feature files with the correct `@tdd_expected_fail @tdd_issue
  @tdd_issue_<N>` tag system. Scenarios whose referenced bugs were already fixed
@@ -110,13 +111,6 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
  `docs/development/automation-tracking.md` and the new
  `docs/development/docs-writer.md` reference.

- **ACMS / UKO API Documentation** (`docs/api/acms.md`): Added comprehensive API
-  reference for the `cleveragents.acms` package covering the four-layer UKO ontology
-  hierarchy, `VocabularyRegistry`, `ProvenanceInfo`, `UKOClass`, `UKOProperty`,
-  `UKOVocabulary`, `Layer2Dependency`, `ParadigmVocabulary`, `DetailLevelMapBuilder`,
-  and all Layer 3 language vocabulary types (Python, TypeScript, Rust, Java).
-  The new page is linked from the API Reference index and the MkDocs navigation.
-
 ### Changed

 - **Decision Tree Full ULID Display** (#5825): The `agents plan tree` command now
@@ -210,11 +204,6 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
  `pr-merge-pool-supervisor` to the product-builder's supervisor launch list (18 total
  supervisors). Updated all numeric references, pre-flight checklists, and validation logic.

- `ActionRepository.update()` now uses explicit bulk `sa_delete()` + `session.flush()`
-  before re-inserting child rows for `action_arguments` and `action_invariants`, fixing
-  a `sqlite3.IntegrityError: UNIQUE constraint failed` crash when `agents plan use` was
-  called on an action that already had arguments registered via `action create`. (#4197)
-
 ---

 ## [3.8.0] — 2026-04-05
@@ -7,7 +7,6 @@
 * Jeffrey Phillips Freeman <jeffrey.freeman@syncleus.com>
 * Luis Mendes <luis.p.mendes@gmail.com>
 * Rui Hu <rui.hu@cleverthis.com>
-* HAL 9000 <hal9000@cleverthis.com>

 # Details

@@ -1,368 +0,0 @@
-# `cleveragents.acms` — Advanced Context Management System
-
-The `acms` package implements the **Universal Knowledge Ontology (UKO)** vocabulary
-support for the Advanced Context Management System.  It provides a four-layer
-ontology hierarchy for representing code semantics across multiple programming
-languages, enabling actors to reason about large codebases with structured,
-budget-constrained context views.
-
-See [ADR-014](../adr/ADR-014-context-management-acms.md) for the design rationale
-and [`docs/modules/uko-provenance.md`](../modules/uko-provenance.md) for provenance
-tracking details.
-
---
-
-## Architecture Overview
-
-The UKO is organized into four layers:
-
-| Layer | Scope | Examples |
-|-------|-------|---------|
-| **Layer 0** | Universal primitives | `Container`, `Atom`, `Boundary`, `dependsOn` |
-| **Layer 1** | General code domain | `TypeDefinition`, `Callable` |
-| **Layer 2** | Programming paradigms | `uko-oo:`, `uko-func:`, `uko-proc:` |
-| **Layer 3** | Language-specific | `uko-py:`, `uko-ts:`, `uko-rs:`, `uko-java:` |
-
---
-
-## Namespace Prefixes
-
-| Prefix | IRI | Layer |
-|--------|-----|-------|
-| `uko-oo:` | `https://cleveragents.ai/ontology/uko/oo#` | 2 |
-| `uko-func:` | `https://cleveragents.ai/ontology/uko/func#` | 2 |
-| `uko-proc:` | `https://cleveragents.ai/ontology/uko/proc#` | 2 |
-| `uko-py:` | `https://cleveragents.ai/ontology/uko/py#` | 3 |
-| `uko-ts:` | `https://cleveragents.ai/ontology/uko/ts#` | 3 |
-| `uko-rs:` | `https://cleveragents.ai/ontology/uko/rs#` | 3 |
-| `uko-java:` | `https://cleveragents.ai/ontology/uko/java#` | 3 |
-
---
-
-## Core Types
-
-### `ProvenanceInfo`
-
-```python
-from cleveragents.acms import ProvenanceInfo
-
-class ProvenanceInfo(BaseModel):
-    source_resource: str        # IRI of the source resource
-    valid_from: datetime        # When this triple became valid
-    is_current: bool            # Whether this is the current revision
-    created_by: str             # Agent or process that created this
-    revision_chain: list[str]   # Ordered list of prior revision IRIs
-```
-
-Provenance contract attached to every typed triple in the UKO graph.  Enables
-temporal queries and point-in-time ontology state reconstruction.
-
---
-
-### `UKOClass`
-
-```python
-from cleveragents.acms import UKOClass
-
-class UKOClass(BaseModel):
-    uri: str                    # Fully-qualified OWL class URI
-    label: str                  # Human-readable label
-    parent_uri: str | None      # rdfs:subClassOf parent URI
-    description: str = ""       # Optional description
-```
-
-Represents an OWL class definition within a UKO vocabulary.
-
---
-
-### `UKOProperty`
-
-```python
-from cleveragents.acms import UKOProperty
-
-class UKOProperty(BaseModel):
-    uri: str                    # Fully-qualified OWL property URI
-    label: str                  # Human-readable label
-    domain_uri: str             # rdfs:domain class URI
-    range_uri: str              # rdfs:range class URI
-    parent_uri: str | None      # rdfs:subPropertyOf parent URI
-```
-
-Represents an OWL object property definition within a UKO vocabulary.
-
---
-
-### `UKOVocabulary`
-
-```python
-from cleveragents.acms import UKOVocabulary
-
-class UKOVocabulary(BaseModel):
-    prefix: str                         # Namespace prefix (e.g. "uko-py:")
-    iri: str                            # Namespace IRI
-    classes: tuple[UKOClass, ...]       # OWL classes in this vocabulary
-    properties: tuple[UKOProperty, ...]  # OWL properties in this vocabulary
-    layer2_deps: tuple[Layer2Dependency, ...]  # Layer 2 dependencies
-```
-
-Container for a complete UKO vocabulary (classes + properties + dependencies).
-
---
-
-### `Layer2Dependency`
-
-```python
-from cleveragents.acms import Layer2Dependency
-
-class Layer2Dependency(BaseModel):
-    iri: str    # Layer 2 vocabulary IRI this vocabulary depends on
-```
-
-Declares a dependency from a Layer 3 vocabulary on a Layer 2 paradigm vocabulary.
-
---
-
-## Layer 2 — Paradigm Vocabularies
-
-### `ParadigmVocabulary`
-
-```python
-from cleveragents.acms import ParadigmVocabulary
-
-class ParadigmVocabulary(BaseModel):
-    prefix: str                         # e.g. "uko-oo:"
-    iri: str                            # Namespace IRI
-    classes: tuple[VocabularyClass, ...]
-    properties: tuple[VocabularyProperty, ...]
-```
-
-Immutable (frozen) Pydantic model for a Layer 2 paradigm vocabulary.
-
-**Built-in paradigm vocabularies:**
-
-```python
-from cleveragents.acms import get_oo_vocabulary, get_func_vocabulary, get_proc_vocabulary
-
-oo_vocab = get_oo_vocabulary()      # Object-Oriented paradigm (uko-oo:)
-func_vocab = get_func_vocabulary()  # Functional paradigm (uko-func:)
-proc_vocab = get_proc_vocabulary()  # Procedural paradigm (uko-proc:)
-```
-
---
-
-### `VocabularyRegistry`
-
-```python
-from cleveragents.acms import VocabularyRegistry, DuplicateVocabularyError
-
-registry = VocabularyRegistry(vocabularies=(get_oo_vocabulary(),))
-
-# Register a vocabulary
-registry.register(get_func_vocabulary())
-
-# Look up by prefix
-vocab = registry.get_by_prefix("uko-oo:")
-
-# Look up by IRI
-vocab = registry.get_by_iri("https://cleveragents.ai/ontology/uko/oo#")
-
-# List all registered prefixes
-prefixes = registry.list_prefixes()
-
-# List all vocabularies
-all_vocabs = registry.list_all()
-
-# Unregister
-registry.unregister("uko-oo:")
-```
-
-**Thread safety:** `VocabularyRegistry` is **not** thread-safe.  Populate once
-during module initialisation under the GIL; do not mutate from multiple threads.
-
-**Raises:** `DuplicateVocabularyError` if a vocabulary with the same prefix or IRI
-is already registered.
-
---
-
-## Detail Level Maps
-
-Detail level maps control how much semantic detail is included in context views
-for each code construct.  They form an inheritance chain: Layer 3 maps extend
-Layer 2 maps, which extend Layer 1 maps.
-
-### Built-in Maps
-
-```python
-from cleveragents.acms import (
-    CODE_DETAIL_LEVEL_MAP,   # Layer 1 general code domain
-    OO_DETAIL_LEVEL_MAP,     # Layer 2 Object-Oriented
-    FUNC_DETAIL_LEVEL_MAP,   # Layer 2 Functional
-    PROC_DETAIL_LEVEL_MAP,   # Layer 2 Procedural
-)
-```
-
-Each map is a `DetailLevelMap` with a `.levels` dict mapping level names to
-integer depth values.
-
-### `DetailLevelMapBuilder`
-
-```python
-from cleveragents.acms import DetailLevelMapBuilder
-
-builder = DetailLevelMapBuilder(parent=OO_DETAIL_LEVEL_MAP)
-builder.insert("uko-py:decorator", depth=3)
-builder.insert("uko-py:type_stub", depth=4)
-py_map = builder.build()
-```
-
-Builds a new `DetailLevelMap` by inserting level entries into a parent map.
-
-### `build_detail_level_map`
-
-```python
-from cleveragents.acms import build_detail_level_map
-
-level_map = build_detail_level_map(
-    parent=OO_DETAIL_LEVEL_MAP,
-    insertions=[("uko-py:decorator", 3), ("uko-py:type_stub", 4)],
-)
-```
-
-Functional alternative to `DetailLevelMapBuilder`.
-
-### `build_effective_map`
-
-```python
-from cleveragents.acms import build_effective_map
-
-effective = build_effective_map(
-    parent=OO_DETAIL_LEVEL_MAP,
-    child=PYTHON_DETAIL_LEVELS,
-)
-```
-
-Merges a parent map and a child map into a single effective map, with child
-entries taking precedence over parent entries.
-
-### `resolve_detail_level`
-
-```python
-from cleveragents.acms import resolve_detail_level
-
-depth = resolve_detail_level(
-    name="uko-py:function",
-    maps=[PYTHON_DETAIL_LEVELS, OO_DETAIL_LEVEL_MAP, CODE_DETAIL_LEVEL_MAP],
-)
-```
-
-Walks the inheritance chain (Layer 3 → Layer 2 → Layer 1) to resolve a named
-detail level to its integer depth.  Returns `None` if not found in any map.
-
---
-
-## Layer 3 — Language Vocabularies
-
-### Python (`uko-py:`)
-
-```python
-from cleveragents.acms import (
-    PYTHON_VOCABULARY,    # ParadigmVocabulary for Python
-    PYTHON_DETAIL_LEVELS, # DetailLevelMap for Python
-    PythonModule,
-    PythonClass,
-    PythonFunction,
-    PythonDecorator,
-    PythonTypeStub,
-)
-```
-
-| Class | Parent | Description |
-|-------|--------|-------------|
-| `PythonModule` | `uko-oo:Module` | A Python `.py` module |
-| `PythonClass` | `uko-oo:Class` | A Python class definition |
-| `PythonFunction` | `uko-oo:Method` | A Python function or method |
-| `PythonDecorator` | `uko-oo:Annotation` | A Python decorator |
-| `PythonTypeStub` | `uko-oo:Interface` | A `.pyi` type stub |
-
-### TypeScript (`uko-ts:`)
-
-```python
-from cleveragents.acms import (
-    TYPESCRIPT_VOCABULARY,
-    TYPESCRIPT_DETAIL_LEVELS,
-    TypeScriptModule,
-    TypeScriptClass,
-    TypeScriptFunction,
-    TypeScriptInterface,
-)
-```
-
-### Rust (`uko-rs:`)
-
-```python
-from cleveragents.acms import (
-    RUST_VOCABULARY,
-    RUST_DETAIL_LEVELS,
-    RustStruct,
-    RustTrait,
-    RustImpl,
-    RustFunction,
-    RustDeriveAttribute,
-)
-```
-
-### Java (`uko-java:`)
-
-```python
-from cleveragents.acms import (
-    JAVA_VOCABULARY,
-    JAVA_DETAIL_LEVELS,
-    JavaClass,
-    JavaInterface,
-    JavaMethod,
-    JavaAnnotation,
-    JavaCheckedException,
-)
-```
-
---
-
-## Usage Example
-
-```python
-from cleveragents.acms import (
-    VocabularyRegistry,
-    get_oo_vocabulary,
-    get_func_vocabulary,
-    PYTHON_VOCABULARY,
-    PYTHON_DETAIL_LEVELS,
-    OO_DETAIL_LEVEL_MAP,
-    resolve_detail_level,
-)
-
-# Build a registry with Layer 2 paradigm vocabularies
-registry = VocabularyRegistry(
-    vocabularies=(
-        get_oo_vocabulary(),
-        get_func_vocabulary(),
-    )
-)
-
-# Resolve a detail level for a Python function
-depth = resolve_detail_level(
-    name="uko-py:function",
-    maps=[PYTHON_DETAIL_LEVELS, OO_DETAIL_LEVEL_MAP],
-)
-print(f"Python function detail depth: {depth}")
-
-# Look up a vocabulary by prefix
-oo_vocab = registry.get_by_prefix("uko-oo:")
-print(f"OO vocabulary has {len(oo_vocab.classes)} classes")
-```
-
---
-
-> **Note:** The ACMS module is internal to the context assembly pipeline.
-> Direct use is only needed when implementing custom context strategies.
-> For typical usage, configure context policies via `agents context` CLI
-> commands — see the [Specification](../specification.md) for details.
@@ -1,618 +0,0 @@
-# `cleveragents.action` — Action Configuration Schema API
-
-The `action` package provides the YAML configuration schema, validation
-pipeline, and loader for CleverAgents **actions** — reusable plan templates
-that define how a task is strategized, executed, reviewed, and completed.
-
-See [`docs/schema/action.schema.yaml`](../../schema/action.schema.yaml) for
-the formal schema definition and
-[`docs/reference/action_cli.md`](../reference/action_cli.md) for the
-companion CLI reference.
-
---
-
-## Overview
-
-Actions are the primary unit of reusable work in CleverAgents. Each action
-is defined by a YAML configuration file that specifies:
-
- **Identity** — a namespaced name, description, and optional long description.
- **Lifecycle actors** — which actors handle each phase (Strategize, Execute,
-  Estimate, Review, Apply, Invariant reconciliation).
- **Completion criteria** — a testable definition of done.
- **Behaviour flags** — whether the action is reusable and/or read-only.
- **Arguments** — typed, validated parameters supplied at plan-use time.
- **Invariants** — constraints propagated as plan-level invariants.
- **Automation profile** — default profile for derived plans.
- **Inputs schema** — optional JSON Schema for advanced input validation.
-
-Actions are created exclusively via YAML files:
-
-```bash
-agents action create --config action.yaml
-```
-
---
-
-## `ActionConfigSchema`
-
-```python
-from cleveragents.action.schema import ActionConfigSchema
-```
-
-Pydantic model representing a fully parsed and validated action YAML file.
-Instances are created via the factory class methods below — never
-instantiated directly.
-
-### Factory Methods
-
-#### `ActionConfigSchema.from_yaml(yaml_string)`
-
-Parse and validate a raw YAML string.
-
-```python
-config = ActionConfigSchema.from_yaml(yaml_string)
-```
-
-| Parameter | Type | Description |
-|-----------|------|-------------|
-| `yaml_string` | `str` | Raw YAML content. Must be a non-empty mapping. |
-
-**Returns:** `ActionConfigSchema`
-
-**Raises:**
-
-| Exception | Condition |
-|-----------|-----------|
-| `ValueError` | YAML string is `None`, empty, or not a mapping. |
-| `pydantic.ValidationError` | One or more fields fail schema validation. |
-
---
-
-#### `ActionConfigSchema.from_yaml_file(path)`
-
-Load and validate an action YAML file from disk.
-
-```python
-config = ActionConfigSchema.from_yaml_file(Path("examples/actions/simple.yaml"))
-```
-
-| Parameter | Type | Description |
-|-----------|------|-------------|
-| `path` | `str \| Path` | Path to the YAML file. |
-
-**Returns:** `ActionConfigSchema`
-
-**Raises:**
-
-| Exception | Condition |
-|-----------|-----------|
-| `FileNotFoundError` | File does not exist at the given path. |
-| `ValueError` | Path is `None`, points to a directory, or content is invalid. |
-| `pydantic.ValidationError` | One or more fields fail schema validation. |
-
---
-
-### Pre-validation Processing
-
-Before Pydantic validation runs, the loader applies three normalisation steps
-in order:
-
-1. **camelCase → snake_case key normalisation** — legacy camelCase keys (e.g.
-   `strategyActor`) are silently converted to their snake_case equivalents and
-   a `WARNING` is emitted via the `cleveragents.action.schema` logger.
-2. **`${ENV_VAR}` interpolation** — any `${VAR}` placeholder in a string value
-   is replaced with the corresponding environment variable. Missing variables
-   are left as-is (no error); resolution is deferred to runtime.
-3. **Invariant normalisation** — invariant strings are trimmed, blank entries
-   are dropped, and duplicates are removed (order-preserving).
-
---
-
-## Schema Reference
-
-### Identity Fields
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `schema_version` | `str` | No | `"1"` | Schema version for forward compatibility. |
-| `name` | `str` | **Yes** | — | Namespaced action name: `namespace/name`. Only lowercase alphanumeric, hyphens, and underscores. |
-| `description` | `str` | **Yes** | — | Short, one-line description of the action. |
-| `long_description` | `str \| None` | No | `None` | Detailed multi-line description. |
-
-#### `name` format
-
-Names must match `^[a-z0-9][a-z0-9_-]*/[a-z0-9][a-z0-9_-]*$`.
-
-```yaml
-name: local/lint-check          # valid
-name: myorg/security-audit      # valid
-name: LintCheck                 # invalid — missing namespace
-name: local/Lint Check          # invalid — spaces not allowed
-```
-
---
-
-### Lifecycle Actor Fields
-
-All actor references must follow the same `namespace/name` format as `name`.
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `strategy_actor` | `str` | **Yes** | — | Actor for the **Strategize** phase. |
-| `execution_actor` | `str` | **Yes** | — | Actor for the **Execute** phase. |
-| `estimation_actor` | `str \| None` | No | `None` | Actor for pre-execution cost/risk estimation. |
-| `review_actor` | `str \| None` | No | `None` | Actor for reviewing execution results. |
-| `apply_actor` | `str \| None` | No | `None` | Actor for the **Apply** phase. |
-| `invariant_actor` | `str \| None` | No | `None` | Actor for reconciling conflicting invariants. |
-
-!!! note "camelCase aliases"
-    The loader accepts legacy camelCase keys for all actor fields and converts
-    them automatically. See the [Key Normalisation](#key-normalisation) table.
-
---
-
-### Completion Criteria
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `definition_of_done` | `str` | **Yes** | — | Testable criteria defining when the action's work is complete. Must be non-empty. |
-
---
-
-### Behaviour Fields
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `reusable` | `bool` | No | `true` | If `false`, the action is archived after its first use. |
-| `read_only` | `bool` | No | `false` | Restricts the action to read-only tool operations. |
-| `state` | `str` | No | `"available"` | Lifecycle state: `available` or `archived`. `draft` is an internal-only state and is not valid in YAML configs. |
-
---
-
-### `arguments`
-
-An optional list of typed parameters that users supply at plan-use time via
-`agents plan use --arg name=value`.
-
-```yaml
-arguments:
-  - name: target_coverage
-    type: integer
-    required: true
-    description: "Target line coverage percentage"
-    min_value: 0
-    max_value: 100
-  - name: report_format
-    type: string
-    required: false
-    default: "text"
-    validation_pattern: "^(text|json|html)$"
-```
-
-#### `ActionArgumentSchema` fields
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `name` | `str` | **Yes** | — | Argument name. 1–64 characters. Must be a valid identifier (alphanumeric, hyphens, underscores). Used as the key in `--arg name=value`. |
-| `type` | `str` | No | `"string"` | Data type: `string`, `integer`, `float`, `boolean`, or `list`. |
-| `required` | `bool` | No | `false` | Whether the argument must be provided. |
-| `description` | `str` | No | `""` | Human-readable description shown in help text. Max 500 characters. |
-| `default` | `str \| int \| float \| bool \| list[str] \| None` | No | `None` | Default value when the argument is not provided. |
-| `validation_pattern` | `str \| None` | No | `None` | Regex pattern for validating `string` arguments. |
-| `min_value` | `float \| None` | No | `None` | Minimum value for `integer` or `float` arguments. |
-| `max_value` | `float \| None` | No | `None` | Maximum value for `integer` or `float` arguments. |
-
-Extra fields on an argument object are **forbidden** and will raise a
-`ValidationError`.
-
---
-
-### `automation_profile`
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `automation_profile` | `str \| None` | No | `None` | Default automation profile for plans derived from this action (e.g. `trusted`, `supervised`, `local/cautious`). |
-
---
-
-### `invariants`
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `invariants` | `list[str]` | No | `[]` | Constraints propagated as plan-level invariants when the action is used. Strings are trimmed, blanks dropped, and duplicates removed. |
-
-```yaml
-invariants:
-  - "All existing tests must continue to pass"
-  - "Public API signatures must not change without deprecation"
-```
-
---
-
-### `inputs_schema`
-
-| Field | Type | Required | Default | Description |
-|-------|------|----------|---------|-------------|
-| `inputs_schema` | `dict[str, Any] \| None` | No | `None` | Optional JSON Schema object for advanced input validation beyond basic argument types. |
-
-Use `inputs_schema` when argument types alone are insufficient — for example,
-to validate nested objects or enforce enumerated values on complex structures.
-
-```yaml
-inputs_schema:
-  type: object
-  properties:
-    stages:
-      type: array
-      items:
-        type: object
-        required: [name, transform]
-        properties:
-          name:
-            type: string
-          transform:
-            type: string
-    output_format:
-      type: string
-      enum: [csv, json, parquet]
-  required:
-    - stages
-```
-
---
-
-### Key Normalisation
-
-The loader accepts legacy camelCase keys and converts them to snake_case.
-A `WARNING` is logged for each converted key.
-
-| camelCase (deprecated) | snake_case (canonical) |
-|------------------------|------------------------|
-| `strategyActor` | `strategy_actor` |
-| `executionActor` | `execution_actor` |
-| `estimationActor` | `estimation_actor` |
-| `reviewActor` | `review_actor` |
-| `applyActor` | `apply_actor` |
-| `invariantActor` | `invariant_actor` |
-| `definitionOfDone` | `definition_of_done` |
-| `longDescription` | `long_description` |
-| `readOnly` | `read_only` |
-| `automationProfile` | `automation_profile` |
-| `inputsSchema` | `inputs_schema` |
-| `validationPattern` | `validation_pattern` |
-| `minValue` | `min_value` |
-| `maxValue` | `max_value` |
-| `schemaVersion` | `schema_version` |
-
---
-
-## Complete Schema at a Glance
-
-```yaml
-# Required fields only
-name: namespace/action-name           # required — namespace/name format
-description: "Short description"      # required
-strategy_actor: namespace/actor-name  # required — namespace/name format
-execution_actor: namespace/actor-name # required — namespace/name format
-definition_of_done: |                 # required — non-empty
-  Measurable completion criteria.
-
-# Optional fields (shown with defaults)
-schema_version: "1"
-long_description: null
-estimation_actor: null
-review_actor: null
-apply_actor: null
-invariant_actor: null
-reusable: true
-read_only: false
-state: available
-automation_profile: null
-arguments: []
-invariants: []
-inputs_schema: null
-```
-
-Extra top-level keys are **forbidden** and will raise a `ValidationError`.
-
---
-
-## Examples
-
-### Minimal Action
-
-The smallest valid action — only required fields:
-
-```yaml
-# examples/actions/simple.yaml
-name: local/lint-check
-description: "Run linting checks on the project"
-
-strategy_actor: local/strategist
-execution_actor: local/executor
-
-definition_of_done: |
-  All linting checks pass with zero errors.
-
-reusable: true
-read_only: true
-```
-
---
-
-### Action with Estimation and Review Actors
-
-Adds optional `estimation_actor` and `review_actor`, typed `arguments`, an
-`automation_profile`, and `invariants`:
-
-```yaml
-# examples/actions/estimation-actor.yaml
-name: local/large-refactor
-description: "Large-scale code refactoring with cost estimation"
-long_description: |
-  Performs a large-scale refactoring of a codebase module. An estimation
-  actor runs after Strategize to predict cost, risk, and duration before
-  execution proceeds.
-
-strategy_actor: local/strategist
-execution_actor: local/executor
-estimation_actor: local/estimator
-review_actor: local/reviewer
-
-definition_of_done: |
-  Refactoring complete. All tests pass. No regressions introduced.
-  Code review approved by the review actor.
-
-reusable: true
-read_only: false
-
-arguments:
-  - name: target_module
-    type: string
-    required: true
-    description: "Module path to refactor"
-  - name: max_files_changed
-    type: integer
-    required: false
-    description: "Maximum number of files to modify"
-    default: 50
-    min_value: 1
-    max_value: 500
-
-automation_profile: trusted
-
-invariants:
-  - "All existing tests must continue to pass"
-  - "Public API signatures must not change without deprecation"
-```
-
---
-
-### Read-Only Investigation Action
-
-Suitable for audits and architecture reviews that must not modify any files:
-
-```yaml
-# examples/actions/read-only.yaml
-name: local/architecture-review
-description: "Review project architecture and produce a report"
-long_description: |
-  Analyzes the project structure, dependency graph, and code patterns
-  to produce an architecture review report. Does not modify any files.
-
-strategy_actor: local/strategist
-execution_actor: local/executor
-
-definition_of_done: |
-  Architecture review report generated covering:
-  - Module dependency graph
-  - Layer boundary compliance
-  - Circular dependency detection
-  - Code duplication analysis
-
-reusable: true
-read_only: true
-state: available
-```
-
---
-
-### Action with `inputs_schema`
-
-Uses `inputs_schema` for complex nested validation beyond basic argument types:
-
-```yaml
-# examples/actions/inputs-schema.yaml
-name: local/data-pipeline
-description: "Build and validate a data processing pipeline"
-
-strategy_actor: local/strategist
-execution_actor: local/executor
-
-definition_of_done: |
-  Pipeline runs end-to-end successfully. All stages produce valid
-  output. Data quality checks pass on final output.
-
-arguments:
-  - name: pipeline_name
-    type: string
-    required: true
-    description: "Name of the pipeline to build"
-  - name: dry_run
-    type: boolean
-    required: false
-    description: "Run in dry-run mode without writing output"
-    default: false
-
-inputs_schema:
-  type: object
-  properties:
-    stages:
-      type: array
-      items:
-        type: object
-        properties:
-          name:
-            type: string
-          transform:
-            type: string
-        required: [name, transform]
-    output_format:
-      type: string
-      enum: [csv, json, parquet]
-  required:
-    - stages
-```
-
---
-
-### Action with Multiple Invariants and `invariant_actor`
-
-Demonstrates `invariant_actor`, `validation_pattern` on a string argument,
-and a rich invariant list:
-
-```yaml
-# examples/actions/invariant-heavy.yaml
-name: local/security-audit
-description: "Comprehensive security audit of a project"
-
-strategy_actor: local/security-strategist
-execution_actor: local/security-scanner
-invariant_actor: local/invariant-resolver
-
-definition_of_done: |
-  All critical and high severity findings have been identified.
-  A complete security report has been generated with severity
-  classifications and remediation steps for each finding.
-
-arguments:
-  - name: severity_threshold
-    type: string
-    required: false
-    description: "Minimum severity to include in report"
-    default: "low"
-    validation_pattern: "^(critical|high|medium|low|informational)$"
-  - name: auto_fix
-    type: boolean
-    required: false
-    description: "Automatically create fix plans for critical findings"
-    default: false
-
-automation_profile: supervised
-
-invariants:
-  - "Never modify production database schemas during audit"
-  - "Never execute discovered exploit code against live systems"
-  - "All findings must include reproducible steps"
-  - "Secrets found during scanning must be redacted in reports"
-  - "Remediation fixes must not break existing tests"
-```
-
---
-
-## Python API Usage
-
-```python
-from pathlib import Path
-from cleveragents.action.schema import ActionConfigSchema
-
-# Load from a file
-config = ActionConfigSchema.from_yaml_file(Path("examples/actions/simple.yaml"))
-
-print(config.name)             # "local/lint-check"
-print(config.strategy_actor)  # "local/strategist"
-print(config.read_only)        # True
-print(config.reusable)         # True
-
-# Load from a YAML string
-yaml_str = """
-name: local/my-action
-description: My action
-strategy_actor: local/strategist
-execution_actor: local/executor
-definition_of_done: Task is complete.
-"""
-config = ActionConfigSchema.from_yaml(yaml_str)
-
-# Access arguments
-for arg in config.arguments:
-    print(arg.name, arg.type, arg.required)
-```
-
-### Environment Variable Interpolation
-
-String values may reference environment variables using `${VAR}` syntax.
-Unresolved variables are left as-is:
-
-```yaml
-name: local/deploy
-description: "Deploy to ${TARGET_ENV}"
-strategy_actor: local/strategist
-execution_actor: local/executor
-definition_of_done: "Deployment to ${TARGET_ENV} complete."
-automation_profile: ${DEPLOY_PROFILE}
-```
-
-```python
-import os
-os.environ["TARGET_ENV"] = "staging"
-os.environ["DEPLOY_PROFILE"] = "supervised"
-
-config = ActionConfigSchema.from_yaml_file(Path("deploy.yaml"))
-# config.description == "Deploy to staging"
-# config.automation_profile == "supervised"
-```
-
---
-
-## CLI Usage
-
-Actions are managed through the `agents action` command group. See
-[Action CLI Reference](../reference/action_cli.md) for full details.
-
-```bash
-# Create an action from a YAML config file
-agents action create --config action.yaml
-
-# List all available actions
-agents action list
-
-# Filter by namespace or state
-agents action list --namespace local
-agents action list --state available
-
-# Show full details for an action
-agents action show local/lint-check
-agents action show local/lint-check --format json
-
-# Archive (soft-delete) an action
-agents action archive local/old-action
-```
-
---
-
-## Validation Errors
-
-`ActionConfigSchema` produces clear, actionable error messages. Common
-failure modes:
-
-| Scenario | Error |
-|----------|-------|
-| `name` missing namespace | `Invalid action name '…'. Names must follow the namespace/name format` |
-| `strategy_actor` not namespaced | `Invalid actor name '…'. Actor names must follow the namespace/name format` |
-| `state` set to `draft` | `Invalid state 'draft'. Allowed states: archived, available` |
-| Unknown argument `type` | `Invalid argument type '…'. Allowed types: boolean, float, integer, list, string` |
-| Extra top-level key | `Extra inputs are not permitted` |
-| Empty YAML | `YAML string is empty. Provide a valid action YAML configuration.` |
-| Non-mapping YAML | `Action YAML must be a mapping (key: value), got …` |
-
---
-
-## See Also
-
- [`docs/schema/action.schema.yaml`](../../schema/action.schema.yaml) — Formal schema definition
- [Action CLI Reference](../reference/action_cli.md) — `agents action` command group
- [`cleveragents.actor`](actor.md) — Actor system (actors referenced by actions)
- [`cleveragents.config`](config.md) — Application configuration
- [ADR-006 Plan Lifecycle](../adr/ADR-006-plan-lifecycle.md) — Design rationale for the plan/action model
@@ -11,7 +11,6 @@ classes, functions, and exceptions with signatures and usage examples.
 | [`cleveragents.core`](core.md) | Exception hierarchy, error handling, retry patterns, async cleanup |
 | [`cleveragents.a2a`](a2a.md) | Agent-to-Agent (A2A) protocol facade, transport, models, and events |
 | [`cleveragents.actor`](actor.md) | Actor registry, configuration, loader, and compiler |
-| [`cleveragents.action`](action.md) | Action configuration schema, validation pipeline, and YAML loader |
 | [`cleveragents.skills`](skills.md) | Skill framework — schema, protocol, registry, discovery, and inline executor |
 | [`cleveragents.tool`](tool.md) | Tool runtime, lifecycle, registry, router, and container executor |
 | [`cleveragents.mcp`](mcp.md) | Model Context Protocol (MCP) adapter, client, registry, and sandbox |
@@ -19,7 +18,6 @@ classes, functions, and exceptions with signatures and usage examples.
 | [`cleveragents.config`](config.md) | Application settings, logging, metrics, and security scanning |
 | [`cleveragents.providers`](providers.md) | AI provider registry — discovery, selection, LLM factory, and capability metadata |
 | [`cleveragents.tui`](tui.md) | Interactive Terminal UI — app, persona system, input routing, slash commands, session export/import |
-| [`cleveragents.acms`](acms.md) | Advanced Context Management System — UKO vocabulary registry, Layer 2/3 paradigm and language vocabularies, detail level maps |

 > **Note:** Internal modules (prefixed with `_`) and implementation details
 > not listed in a module's `__all__` are considered private and may change
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
HAL9000	1e543e8fa3	docs(development): add developer setup guide CI / build (pull_request) Successful in 22s Details CI / lint (pull_request) Successful in 32s Details CI / quality (pull_request) Successful in 51s Details CI / push-validation (pull_request) Successful in 21s Details CI / helm (pull_request) Successful in 29s Details CI / typecheck (pull_request) Successful in 1m0s Details CI / security (pull_request) Successful in 1m1s Details CI / e2e_tests (pull_request) Successful in 3m7s Details CI / integration_tests (pull_request) Successful in 7m3s Details CI / unit_tests (pull_request) Successful in 7m50s Details CI / docker (pull_request) Successful in 10s Details CI / coverage (pull_request) Successful in 15m59s Details CI / status-check (pull_request) Successful in 1s Details Add comprehensive developer setup guide covering prerequisites, development workflow, testing, linting, type checking, commit guidelines, devcontainer setup, and troubleshooting. Refs: #9123	2026-04-14 08:12:26 +00:00
HAL9000	1031fd0fb1	fix(agents): make bug-hunt-pool-supervisor tracking non-blocking to prevent initialization hangs CI / lint (pull_request) Successful in 25s Details CI / typecheck (pull_request) Successful in 59s Details CI / quality (pull_request) Successful in 33s Details CI / security (pull_request) Successful in 55s Details CI / build (pull_request) Successful in 44s Details CI / helm (pull_request) Successful in 30s Details CI / push-validation (pull_request) Successful in 26s Details CI / integration_tests (pull_request) Successful in 4m13s Details CI / e2e_tests (pull_request) Successful in 4m19s Details CI / unit_tests (pull_request) Successful in 6m13s Details CI / docker (pull_request) Successful in 13s Details CI / coverage (pull_request) Successful in 14m50s Details CI / status-check (pull_request) Successful in 1s Details	2026-04-14 05:25:30 +00:00