agentleFS
kunalsurikunalsuri/ai-fication-kit/.claude/skills/review-agent-config/SKILL.md

review-agent-config

Skill3 starsChanged 4 months agoApache-2.0View on GitHub

Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the review-agent-config diagnostic.

    line 8
  2. Distinctive:

    Does not auto-edit CLAUDE.md or AGENTS.md.

    line 101
  3. Very specific:

    Does not check ai/guide/ content quality — that is /post-cold-start-verification.

    line 102
  4. Very specific:

    Does not assess overall AI-layer maturity — that is /verify-ai-readiness.

    line 103
  5. Distinctive:

    Does not run builds or tests.

    line 104

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
<!-- Copyright (c) 2026 Kunal Suri (CEA LIST). All rights reserved. -->

Run the review-agent-config diagnostic. Read-only. Produce a structured findings report; do NOT edit any file.

Inputs — read these files (and only these)

  1. CLAUDE.md (project root) — full read
  2. AGENTS.md (project root) — full read
  3. package.json (project root) — grep for "build" and "test" script keys only
  4. pom.xml (project root, if present) — grep <build> section only
  5. ai/guide/MODULE_MAP.md — check existence on disk; no deep read needed
  6. ai/INDEX.md — check existence on disk; no deep read needed
  7. Any ai/guide/*.md paths referenced in the knowledge-map sections — existence check only via Glob

Checks

Section A — CLAUDE.md structure

IDCheckSeverity
C1Contains the literal @AGENTS.md directive (not just a comment or a markdown link [AGENTS.md](AGENTS.md))❌
C2Has a "Hard rules" or equivalent section❌
C3Has a "Where to look" or knowledge-map section with explicit pointers into ai/guide/❌
C4Has a token-discipline or subagent-delegation section⚠️
C5No unfilled placeholders: regex <[a-zA-Z ]{3,}>, bare TODO, or the literal string fill in❌
C6Build command is present and not a placeholder❌
C7Test command is present and not a placeholder❌
C8Test locations are filled in (not <fill in during cold start> or equivalent)❌
C9No reference to CLAUDE_bkp_*.md files framed as active guidance (stale post-cold-start)⚠️
C10No Claude-specific directives duplicated wholesale from AGENTS.md⚠️

Section B — AGENTS.md structure

IDCheckSeverity
A1Contains no Claude Code-specific directives (@import, memory syntax, hook syntax)⚠️
A2Hard rule present: frozen upstream / don't touch inherited code❌
A3Hard rule present: test before done — with actual build and test commands❌
A4Hard rule present: surgical diffs❌
A5Hard rule present: provenance tagging ([inferred] / [verified])❌
A6Hard rule present: no phantom bugs / config churn❌
A7Hard rule present: verify claims before declaring done❌
A8Hard rule present: license-header matching for new files⚠️
A9Has a knowledge-map section pointing to ai/guide/❌
A10No unfilled placeholders (same regex as C5)❌
A11No reference to AGENTS_bkp_*.md files framed as active guidance⚠️

Section C — Cross-file consistency

IDCheckSeverity
X1Build command in CLAUDE.md matches build command in AGENTS.md❌
X2Test command in CLAUDE.md matches test command in AGENTS.md❌
X3Build/test commands match what package.json scripts or pom.xml actually define⚠️
X4At least one ai/guide/ path mentioned in any knowledge-map section resolves on disk❌
X5No rule in CLAUDE.md directly contradicts a rule in AGENTS.md❌
X6"Repo intelligence" / ai-layer description is not copy-pasted verbatim into both files⚠️

Output format

Emit the report directly to the user (do NOT write a file). Use this structure exactly:

review-agent-config — findings
══════════════════════════════════════════════════

CLAUDE.md
─────────
✅/⚠️/❌  <check ID> <check name>
           → <one-line concrete fix>   ← omit this line for ✅

AGENTS.md
─────────
✅/⚠️/❌  <check ID> <check name>
           → <one-line concrete fix>

Cross-file
──────────
✅/⚠️/❌  <check ID> <check name>
           → <one-line concrete fix>

Summary
───────
X passed · Y warnings · Z errors
Next step: <single highest-priority action — one sentence>

Reporting discipline

  • Report every check, not just failures. Passing checks build confidence.
  • For every ❌ or ⚠️, always include a concrete one-line fix — never just "this is wrong." Name the exact line or section to change.
  • The "Next step" must name only the single highest-priority action. Do not list all failures again.
  • Severity governs the icon only; a ⚠️ warning is still reported and still gets a fix suggestion.

What this skill does NOT do

  • Does not auto-edit CLAUDE.md or AGENTS.md.
  • Does not check ai/guide/ content quality — that is /post-cold-start-verification.
  • Does not assess overall AI-layer maturity — that is /verify-ai-readiness.
  • Does not run builds or tests.

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.