agentleFS
scoobydont-666scoobydont-666/shared-claude-skills/skills/config-auditor/SKILL.md

config-auditor

Skill1 starsChanged 32 days agoMITView on GitHub

Audit configuration, project instructions, registries and skill references for contradictions, stale claims and missing dependencies.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the user-named repositories and applicable project instructions.

    line 7

≈ “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

Configuration coherence audit

Read the user-named repositories and applicable project instructions. Inventory configuration files and their consumers before comparing them. Never assume a global configuration applies to every project.

For each claim, record its file/line, scope, expected consumer and evidence date. Compare declared values with the actual source or an authorized read-only runtime query. Separate desired state, observed state and historical notes.

Check:

  • Conflicting toolchain versions, endpoints, feature defaults, permissions and installation paths.
  • References to absent files, skills, commands, services or generated artifacts.
  • Duplicated settings whose precedence differs between clients.
  • Stale examples, retired components, unsupported model or price claims.
  • Secrets and personal information in sample configuration or logs.

Classify each finding as confirmed contradiction, stale claim, missing dependency or unknown. Do not resolve unknowns by choosing the newest-looking file. Identify the owner and authoritative source.

Propose the smallest correction, preview its consumers, and edit only authorized paths. Verify the rendered configuration and the consuming path after a change. Report findings with evidence and unresolved questions; unavailable runtime access is not a passing audit.

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.