Claude Md Audit

What it does

When your agent uses it

• The user asks to audit
• Verify CLAUDE.md files
• Says is my CLAUDE.md still accurate
• Flags possible doc drift

Example prompts

• “is my CLAUDE.md still accurate”
• “/claude-md-audit”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash(python:*)

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit cb80eae. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • Bash(python:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Md Audit loads about 649 tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 260 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~137

When it runs · the whole SKILL.md, loaded when a task matches

~649

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from timothywarner-org/claude-code at commit cb80eae, republished under its MIT licence (© timothywarner-org). 260 words, ~649 tokens.

name

claude-md-audit

description

Audit the CLAUDE.md hierarchy in a repo for drift between what each CLAUDE.md claims and what's actually on disk. Validates that referenced file paths still exist, flags voice violations (em dashes, "ask" as a noun), and checks the ground-truth facts block for stale tokens (MCP spec date, transports, model lineup). Use when the user asks to audit, validate, check, or verify CLAUDE.md files, says "is my CLAUDE.md still accurate", flags possible doc drift, or wants to sanity-check the docs before a course recording or release.

allowed-tools

Read, Glob, Grep, Bash(python:*)

argument-hint

[--fix] [--scope=root|segment_1|segment_2|segment_3|segment_4|all]

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

© timothywarner-org, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, references) in .claude/skills/claude-md-audit of timothywarner-org/claude-code.

• SKILL.md
• references/CLAUDE_MD_PATTERNS.md
• scripts/audit_claude_md.py

Open the folder on GitHubat commit cb80eae