claude-md-audit

claude-md-audit is a command for Claude Code from fablerlabs/claude-md-templates. It costs 24 tokens per session (568 once invoked), scanned A, original, MIT.

A command that grades a repository's CLAUDE.md or AGENTS.md file, which contains instructions for coding agents working in that repository. It gives a score and lists the most important fixes first.

In plain words
What is it for?
Use it to review agent rules, verify run, test, lint, and build commands, check the repository map, and produce a worst-first improvement list.
Why use it?
It finds missing, vague, or inaccurate instructions that can make an agent use the wrong commands or misunderstand the project layout. It checks documented commands against the repository's actual files and configuration.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-md-kit plugin — 3 commands shipped together

Good fit Use it to review agent rules, verify run, test, lint, and build commands, check the repository map, and produce a worst-first improvement list.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add fablerlabs/claude-md-templates
Claude Code
/plugin install claude-md-kit

Made for: Claude Code.

Or install claude-md-kit, the plugin that ships this one along with the rest of its 3 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-md-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/fablerlabs/claude-md-templates/claude-md-audit/github.svg)](https://agentmods.dev/commands/fablerlabs/claude-md-templates/claude-md-audit)
Your own site
<a href="https://agentmods.dev/commands/fablerlabs/claude-md-templates/claude-md-audit"><img src="https://agentmods.dev/badge/commands/fablerlabs/claude-md-templates/claude-md-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-md-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/fablerlabs/claude-md-templates/claude-md-audit"><img src="https://agentmods.dev/badge/commands/fablerlabs/claude-md-templates/claude-md-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00568
Opus 5 $0.00012 $0.00284
Sonnet 5 $0.00005 $0.00114
Haiku 4.5 $0.00002 $0.00057

Measured 10d ago against content hash 34efa53f0eb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-md-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

and read output, curl the endpoint, screenshot) — not just typecheck.
commands/claude-md-audit.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit this repository's agent rules file (CLAUDE.md, or AGENTS.md if that's what exists; the user may pass an explicit path in arguments). If neither exists, say so and suggest /claude-md-new, then stop.

Read the rules file AND spot-check it against reality: open the manifests/CI configs it references (or should reference) and verify the commands it lists actually exist. A rules file that lies is worse than none. Grading standards live in ${CLAUDE_PLUGIN_ROOT}/FIELD-GUIDE.md — read it before scoring.

Rubric — score each, then sum (0–100)

  1. Commands (0–25). Exact run / test / single-test / lint / build commands present and REAL (verified against package.json scripts, Makefile, CI, etc.). Deduct for missing single-test invocation, wrong or invented commands.
  2. Map of the repo (0–20). Says where things live and where new code should go — specific paths, not descriptions. Deduct for anything an agent could only learn by asking.
  3. Non-obvious conventions (0–20). The rules a new hire would have to be told: invariants, footguns, "we do X here, not Y", what NOT to touch. Deduct for generic advice ("write tests", "follow best practices") — each wish-list line is negative signal.
  4. Verification loop (0–15). Tells the agent how to prove a change works (run tests and read output, curl the endpoint, screenshot) — not just typecheck.
  5. Terseness & altitude (0–10). Imperative bullets, no prose padding, ~30–80 lines. Deduct for paragraphs of philosophy or duplicated README content.
  6. Freshness (0–10). References match the current tree (paths exist, scripts still in package.json, stack versions not stale).

Output format

  • Score: N/100 with the six sub-scores on one line each.
  • Worst-first fixes: numbered list; each item = the problem, why it costs agent performance, and the concrete replacement text (write the actual lines, ready to paste).
  • Verified-command check: table of every command in the file → found-in / not-found.
  • Offer to apply the fixes directly if the user wants.

Read the full file on GitHub · 43 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 43 lines · 24 tokens per session scan A 34efa53f0eb2

Subscribe to this mod's changes

claude-md-audit is a command published in the GitHub repository fablerlabs/claude-md-templates (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 568 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.