audit-claude-md

audit-claude-md is a skill for Claude Code from marcusgoll/Spec-Flow. It costs 0 tokens per session (666 once invoked), scanned A, original, MIT.

A command for reviewing and restructuring CLAUDE.md files, which contain instructions for Claude Code in a project or folder.

In plain words
What is it for?
Use it to audit instruction files, apply length and clarity checks, and create folder-specific guidance for complex parts of a project.
Why use it?
It identifies excessive length, vague wording, and missing sections that can make instructions harder for the assistant to follow.

Skill for Claude Code

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

Good fit Use it to audit instruction files, apply length and clarity checks, and create folder-specific guidance for complex parts of a project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcusgoll/spec-flow/audit-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.

Any agent
npx skills add marcusgoll/Spec-Flow --skill audit-claude-md
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

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 audit-claude-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusgoll/spec-flow/audit-claude-md/github.svg)](https://agentmods.dev/skills/marcusgoll/spec-flow/audit-claude-md)
Your own site
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/audit-claude-md"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/audit-claude-md/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 audit-claude-md

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/audit-claude-md"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/audit-claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 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. 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 $0.00666
Opus 5 $0.00000 $0.00333
Sonnet 5 $0.00000 $0.00133
Haiku 4.5 $0.00000 $0.00067

Measured 9d ago against content hash 298d8b789fd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-claude-md 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 9d 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/skills/audit-claude-md/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

audit-claude-md Skill

Audit and refactor CLAUDE.md files to eliminate bloat, enforce context engineering best practices, and create folder-level CLAUDE.md files for complex domain-specific instructions.

Quick Start

Run the audit command to analyze all CLAUDE.md files:

/audit-claude-md

Or audit a specific file:

/audit-claude-md path/to/CLAUDE.md

What This Audits

Line Count Analysis

File Type Warning Maximum
Feature CLAUDE.md 100 lines 200 lines
Project CLAUDE.md 150 lines 300 lines
Root CLAUDE.md 300 lines 400 lines

Vague Language Detection

Prohibited patterns that degrade LLM instruction-following:

  • "should probably" → Use MUST, SHOULD, or MAY
  • "might want to" → Be specific or omit
  • "you could" → Use imperative voice
  • "consider maybe" → Decide and state clearly
  • "it's good to" → Use SHOULD or MUST
  • "try to" → State the requirement directly

Required Sections

Root CLAUDE.md must have:

  • ## WHAT This Is - Purpose and scope
  • ## WHY This Approach - Rationale
  • ## HOW To Use It - Instructions

Quality Scoring

Component Weight
Line count 30%
Vague language 25%
Strong modals (MUST/SHOULD/NEVER) 15%
Required sections 15%
External references 10%
Freshness 5%

Grades

  • A (80-100): Excellent - Follows best practices
  • B (60-79): Good - Minor improvements needed
  • C (40-59): Needs Improvement - Significant issues
  • F (0-39): Critical - Major refactoring required

Refactoring Recommendations

If Line Count Exceeds Maximum

  1. Extract deep-dive content to docs/references/
  2. Keep only essential instructions in CLAUDE.md
  3. Add links to reference documentation
  4. Use progressive disclosure pattern

If High Vague Language Count

Replace uncertain language with strong modals:

  • "should probably" → "MUST" or "SHOULD"
  • "might want to" → "Consider" or omit
  • "you could" → Direct imperative

Read the full file on GitHub · 105 lines

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. 9d ago First seen · 105 lines · 0 tokens per session scan A 298d8b789fd8

Subscribe to this mod's changes

audit-claude-md is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 666 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 2026-08-30.

Related

Other skills, from other repositories

android-ui-journey-testing

XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.

sickn33/agentic-awesome-skills · 27 tokens

agent-self-scheduling

Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.

sickn33/agentic-awesome-skills · 24 tokens

clawd-animation-lite

A lightweight generator for short, 1–3 second pixel animations featuring Clawd, the Claude Code mascot, shown as a small coral-orange crab. It creates a complete HTML file that can be opened in a browser.

YiShu5/claude-skills · 190 tokens

clawd-animation

A generator for self-contained HTML pixel animations featuring Clawd, the pixel-style crab mascot of Claude Code. It turns a natural-language scene into a short looping browser animation with a background, character actions, props, and effects.

YiShu5/claude-skills · 208 tokens

self-improving-agent

Low-noise self-improvement skill. Captures learnings, errors, and corrections into a local .learnings/ cache layer. Never auto-promotes to long-term memory files (SOUL.md, MEMORY.md, AGENTS.md, TOOLS.md). Promotion requires explicit user approval after repeated validation.

YiShu5/claude-skills · 68 tokens

HTMLHero.skill

A workflow for building a working, previewable first-page hero section—a prominent opening area of a website—from a prompt, brand direction, and visual requirements. It can work with HTML or React projects and treats the hero as the visual template for later pages.

YiShu5/claude-skills · 107 tokens