claude-md-audit

claude-md-audit is a skill for Claude Code from timothywarner-org/claude-code. It costs 128 tokens per session (666 once invoked), scanned A, original, MIT.

An audit of CLAUDE.md files, which are instruction and memory files used by coding agents in a repository.

In plain words
What is it for?
Use it to check whether the repository’s agent instructions still match the files and configuration on disk.
Why use it?
It finds outdated instructions, references to missing files, writing-rule violations, and stale technical facts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

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.

agentmods
npx agentmods add skills/timothywarner-org/claude-code/claude-md-audit
Any agent
npx skills add timothywarner-org/claude-code --skill claude-md-audit
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/claude-code

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/skills/timothywarner-org/claude-code/claude-md-audit.svg)](https://agentmods.dev/skills/timothywarner-org/claude-code/claude-md-audit)
Your own site
<a href="https://agentmods.dev/skills/timothywarner-org/claude-code/claude-md-audit"><img src="https://agentmods.dev/badge/skills/timothywarner-org/claude-code/claude-md-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00128 $0.00666
Opus 5 $0.00064 $0.00333
Sonnet 5 $0.00026 $0.00133
Haiku 4.5 $0.00013 $0.00067

Measured 6d ago against content hash 2530290e6f82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_claude_md.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/claude-md-audit/SKILL.md · 47 lines

What it actually says

CLAUDE.md hierarchy audit

This skill validates the five-scope CLAUDE.md teaching artifact that Segment 2 of this course centers on. The Python audit script does the heavy lifting; this prompt orchestrates and interprets.

Run the audit

python "${CLAUDE_SKILL_DIR}/scripts/audit_claude_md.py" $ARGUMENTS

How to interpret results

The script outputs JSON. Read the status field first:

  • clean (exit 0): every CLAUDE.md file exists, every referenced path resolves, ground-truth facts block matches expected values. Report a one-line "all clean" and stop.
  • drift (exit 1): one or more findings. Read each entry in the findings array. Each has file, severity (high/medium/low), category, and message.
  • error (exit 2): hard failure (missing repo root, script bug). Report the error and stop.

When drift is found

  1. Load references/CLAUDE_MD_PATTERNS.md - it documents the five canonical patterns and the common drift modes. Read it only when needed (progressive disclosure).
  2. Group findings by severity. Address high first.
  3. For each finding, propose the minimal correction. Cite the file and line.
  4. If the user passed --fix, the script already corrected obvious path typos. Re-run without --fix to confirm.

Voice rules for any rewrites you propose

This is a Tim Warner course repo. Match the voice in segment_4_hero/CLAUDE.md:

  • Bold key terms.
  • No em dashes. Hyphens with spaces, commas, or periods only.
  • Never use "ask" as a noun.
  • Sentence-case headings.
  • First-principles, plain-spoken, mildly irreverent. No corporate-speak.

What the script does NOT check

  • Whether the lesson prose in each CLAUDE.md is pedagogically sound. That's a human judgment.
  • Whether new files added to the repo should be mentioned in a CLAUDE.md. Suggest additions only when the diff is obvious.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 47 lines · 128 tokens per session scan A 2530290e6f82

Subscribe to this mod's changes

claude-md-audit is a skill published in the GitHub repository timothywarner-org/claude-code (223 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 666 once invoked, about $0.0006 per session on Opus 5. 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 2026-08-30.

Related

Other skills, from other repositories

mem0-status

Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.

mem0ai/mem0 · 44 tokens

inspector-workbench

Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…

CopilotKit/CopilotKit · 112 tokens

md-audit

Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…

chaitanyagiri/munder-difflin · 85 tokens

potpie-debug-memory

Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.

potpie-ai/potpie · 41 tokens

exploiting-linux-kernel-vulnerabilities

Methodology for discovering and exploiting Linux kernel memory-corruption vulnerabilities (UAF, OOB read/write, race/TOCTOU, type confusion) during authorized engagements, covering reachability analysis, building stable read/write primitives from a single bug, defeating KASLR/SMEP/SMAP/KPTI, slab/buddy heap grooming…

xalgorix/xalgorix · 96 tokens

exploiting-format-string-vulnerabilities

Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.

xalgorix/xalgorix · 69 tokens