Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moberghr/mtk-agent-toolkit/main/.claude/skills/claude-md-audit/SKILL.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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.
[](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/claude-md-audit)<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/claude-md-audit"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/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.
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/claude-md-audit"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/claude-md-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 26 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Excessive Agency · line 142 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 198 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.02407 |
| Opus 5 | $0.00023 | $0.01203 |
| Sonnet 5 | $0.00009 | $0.00481 |
| Haiku 4.5 | $0.00005 | $0.00241 |
Grade A, and why
claude-md-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/tech-stack 2>/dev/null || echo "(not set)" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Audit
Current Audit Targets
echo "--- Existing CLAUDE.md files ---"
{ find . -maxdepth 6 -name CLAUDE.md -not -path "./.git/*" -not -path "*/node_modules/*" 2>/dev/null; \
find . -maxdepth 4 -name ".claude.local.md" 2>/dev/null; } | sort -u
echo "--- ~/.claude/CLAUDE.md ---"
test -f "$HOME/.claude/CLAUDE.md" && echo "$HOME/.claude/CLAUDE.md ($(wc -l < "$HOME/.claude/CLAUDE.md") lines)" || echo "(absent)"
echo "--- Tech stack ---"
cat .claude/tech-stack 2>/dev/null || echo "(not set)"
Overview
Audit existing CLAUDE.md files against a quality rubric, then propose minimal append-only diffs. This is a re-grade loop, not a regeneration. The skill honors rule S1.5 (CLAUDE.md is protected) — it never overwrites and never rewrites whole sections without explicit user approval.
This skill is distinct from setup-bootstrap (one-time creation of CLAUDE.md
from a fresh codebase scan) and setup-audit (refreshes
architecture-principles.md, not CLAUDE.md). Audit grades intent against
reality; bootstrap creates intent from scratch.
When To Use
- Periodic CLAUDE.md health check (recommended every 4-8 weeks)
- After significant codebase changes that may have invalidated documented commands
- When AI sessions start hitting friction that suggests stale context (broken build commands, references to deleted files, missing recent conventions)
- When the engineer says "CLAUDE.md feels off" or "is the AI seeing the right things?"
When NOT To Use
- First-time setup of a repo — use
/mtk-setup(which runssetup-bootstrap) - Refreshing architecture principles — use
/mtk-setup --audit(which runssetup-audit) - Repos with no CLAUDE.md yet — bootstrap first; audit only re-grades existing intent
- After a single session of edits — the rot worth detecting takes weeks to accumulate; auditing too often manufactures churn
Workflow
Phase 1 — Discovery
The dynamic-context block at the top of this skill already lists target files.
Confirm the inventory before proceeding. If the project root has no CLAUDE.md,
stop and tell the user to run /mtk-setup first — there is no intent to
audit.
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.
- yesterday Changed 55b5ffaeb714
- 10d ago First seen · 227 lines · 45 tokens per session scan A 5d68ad1079f3
claude-md-audit is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 2,407 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…