claude-md-audit

claude-md-audit is a command for Claude Code from adamwstauffer/shidler. It costs 0 tokens per session (321 once invoked), scanned A, original, MIT.

A periodic audit of the project's instruction and memory files, including CLAUDE.md and MEMORY.md. It looks for outdated file paths, conflicting guidance, repeated information, and unnecessary text.

In plain words
What is it for?
Run it after major reorganisations or occasionally to produce a read-only findings report with issue severity, locations, and suggested fixes.
Why use it?
Project instructions and saved notes can become inaccurate as the codebase changes, causing the coding agent to follow unreliable guidance.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Good fit Run it after major reorganisations or occasionally to produce a read-only findings report with issue severity, locations, and suggested fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/adamwstauffer/shidler/claude-md-audit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/adamwstauffer/shidler

Made for: Claude Code.

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/adamwstauffer/shidler/claude-md-audit/github.svg)](https://agentmods.dev/commands/adamwstauffer/shidler/claude-md-audit)
Your own site
<a href="https://agentmods.dev/commands/adamwstauffer/shidler/claude-md-audit"><img src="https://agentmods.dev/badge/commands/adamwstauffer/shidler/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/adamwstauffer/shidler/claude-md-audit"><img src="https://agentmods.dev/badge/commands/adamwstauffer/shidler/claude-md-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00321
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 10d ago against content hash fe6d01090121, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-md-audit scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/claude-md-audit.md · 19 lines

What it actually says

/claude-md-audit — Audit CLAUDE.md + memory for drift

Run periodically (monthly, or right after a courses/ restructure) — not on every change. Detects stale path citations, cross-file contradictions, duplicated facts, and bloat across CLAUDE.md and the memory store.

What this command does

You audit the canonical instruction + memory surface (CLAUDE.md, MEMORY.md, and the memory fact files) and produce a findings report. You are read-only by default — you report and offer fixes; you don't rewrite without approval.

Follow the methodology in .claude/skills/claude-md-audit/SKILL.md end-to-end: run all four checks (stale refs → contradictions → dup/bloat → structural hygiene), group findings by severity with file:line + suggested fix, and route anything you don't fix this session into the report so it isn't lost.

Why a ritual, not a per-change rule

A "check CLAUDE.md on every commit" instruction is the most-skipped kind of rule. Drift is better prevented by single-sourcing facts (one home + pointers) and caught by this periodic scan — especially after this repo's frequent courses/ restructures.

Output

A severity-grouped findings report, ending with: CLAUDE.md audit: <N> stale refs / <N> contradictions / <N> dup-or-bloat / <N> hygiene. <recommendation>.

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 · 19 lines · 0 tokens per session scan A fe6d01090121

Subscribe to this mod's changes

claude-md-audit is a command published in the GitHub repository adamwstauffer/shidler (10 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 321 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.