agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/harness-gc/SKILL.md

harness-gc

Skill2 starsChanged 33 days agoMITView on GitHub

Detects drift across rules, Skills, commands, and docs; proposes evidence-backed harness cleanup

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Look for contradictions (e.g.

    line 17
  2. Very specific:

    Write a report under .agent/evidence/harness-gc-<date>/REPORT.md with:

    line 19
  3. Very specific:

    Product application file changes: always require a separate approved IMPLEMENTATION_PLAN.md (same gate as code-structure-cleanup).

    line 25
  4. Distinctive:

    Do not auto-mutate rules/Skills without Captain approval.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Harness GC

Use this Skill when

Rules, Skills, commands, README, or AGENTS.md appear inconsistent; after a major Compass upgrade; or when the Captain asks for harness garbage collection.

Procedure

  1. Inventory always-on rules (.cursor/rules/), Skills (.cursor/skills/*/SKILL.md), commands (.cursor/commands/*.md), and key docs (AGENTS.md, README, TESTING).
  2. Look for contradictions (e.g. README Skill count vs doctor list, commands that reference missing Skills, failClosed docs vs hooks.json).
  3. Write a report under .agent/evidence/harness-gc-<date>/REPORT.md with:
    • Findings (severity, location, evidence)
    • Recommended fixes
    • Predicted impact / regression risk
  4. Docs-only / control-repo workflow fixes may proceed only with an approved plan when they change shipped Compass behavior.
  5. Product application file changes always require a separate approved IMPLEMENTATION_PLAN.md (same gate as code-structure-cleanup).
  6. Do not auto-mutate rules/Skills without Captain approval.

Output

Harness GC report path and a clear ask: approve a plan, waive findings, or defer.

Prohibited actions

  • Silently editing always-on rules to “fix” drift
  • Expanding into unrelated product refactors
  • Deleting Skills or commands without an approved plan

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free