agentleFS
Sign inStart free
stevenprimo-debugstevenprimo-debug/claude-code-audit/.claude/skills/audit-config/SKILL.md

audit-config

Skill0 starsChanged 3 months agoMITView on GitHub

Audit this Claude Code setup for structural health - skill listing budget overflow, broken hooks, orphaned memory, cross-OS portability. Use when the setup feels wrong, a skill stopped auto-firing, a hook seems dead, or before sharing the repo with someone on another operating system.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. ethereum/execution-specs★ 1.2ksame name
    2. axrmxv/claude-config★ 1same name
    3. ArhamBafna/agent-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the auditor and interpret the result.

    line 14
  2. Distinctive:

    Read the findings. Lead with the errors.

    line 27
  3. Very specific:

    If BG001 fires, it is the finding that matters most.

    line 33
  4. Distinctive:

    Every error has been named with its consequence, not just its code.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Audit this Claude Code setup

Run the auditor and interpret the result. Do not hand the raw dump back — read it and say what is actually wrong.

Steps

  1. Run the audit:

    python ccaudit.py audit --format json

    On Windows use py -3 if python is not on PATH.

  2. Read the findings. Lead with the errors; warnings are context.
  3. For each error, state three things in one line each: what is broken, what breaks because of it, and the fix. The finding already carries a fix and a doc field — use them rather than inventing advice.
  4. If BG001 fires, it is the finding that matters most. Explain the failure mode plainly: the skills are still on disk and still work when typed, but Claude no longer sees their descriptions, so it stopped choosing them on its own. Then list the biggest contributors and which lever fits each one.
  5. Offer to apply the mechanical fixes — disable-model-invocation: true on manual-only skills, CRLF conversion, removing dead hook entries. Do not apply them without a go-ahead: they edit config that other sessions load.

Done when

  • Every error has been named with its consequence, not just its code.
  • The user knows which single fix buys the most.
  • Nothing was edited without approval.

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