How do I install the Claude Md Audit skill?

Run npx skillmds@latest add tomevault-io/claude-md-audit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Claude Md Audit safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Claude Md Audit?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Claude Md Audit free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Claude Md Audit?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Claude Md Audit by tomevault-io — Agent Skill

Name: Claude Md Audit
Author: tomevault-io

Claude Md Audit

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. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

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

Load references/CLAUDE_MD_PATTERNS.md — it documents the five canonical patterns and the common drift modes. Read it only when needed (progressive disclosure).
Group findings by severity. Address high first.
For each finding, propose the minimal correction. Cite the file and line.
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.

Source: timothywarner-org/claude-code — distributed by TomeVault.

---name: claude-md-auditdescription: 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. Use when this capability is needed.---# CLAUDE.md hierarchy auditThis 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 resultsThe 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 found1. **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 proposeThis 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.---> Source: [timothywarner-org/claude-code](https://github.com/timothywarner-org/claude-code) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions