audit-claude-md

Audit and refine CLAUDE.md files to ensure accuracy with codebase.

Command for Claude Code

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 commands/jnarowski/agentcmd/audit-claude-md
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 938 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 $0.00014 $0.00938
Opus 5 $0.00007 $0.00469
Sonnet 5 $0.00003 $0.00188
Haiku 4.5 $0.00001 $0.00094

Measured yesterday against content hash 248fed4f1978, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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/commands/audit-claude-md.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit CLAUDE.md Files

Perform comprehensive but non-destructive audit of CLAUDE.md documentation to ensure alignment with current codebase patterns and best practices. Run weekly or after major refactors.

Variables

  • $target-path: $1 (optional) - Specific CLAUDE.md file or directory to audit (defaults to all)

Instructions

  • This is MAINTENANCE, not reorganization
  • Focus on accuracy, not structure
  • Highlight issues but don't auto-fix (ask first)
  • Verify links to code examples exist
  • Check for outdated patterns or deprecated code
  • Suggest improvements based on actual codebase

Workflow

  1. Discover CLAUDE.md files

    • Find all CLAUDE.md in scope ($target-path or entire repo)
    • List files with locations
  2. Audit each file

    • Link validation
    • Pattern verification
    • Best practice extraction
    • Duplication check
    • Completeness check
  3. Generate audit report

    • Status per file (✅/⚠️/❌)
    • Issues found
    • Suggested improvements
  4. Propose refinements

    • Show specific proposed changes
    • Ask user which to apply
  5. Apply approved changes

    • Update files
    • Report what changed

Audit Checks Per File

Link Validation

  • Extract all file paths from CLAUDE.md
  • Use Glob to verify files exist
  • Check .agent/docs/ references valid
  • Report broken links

Pattern Verification

  • Search codebase for patterns mentioned in docs
  • Verify conventions still followed (imports, naming, architecture)
  • Identify deprecated patterns still documented
  • Find new patterns not yet documented

Detection:

  • Search for old patterns (e.g., "services/project.service")
  • Count occurrences - if 0, pattern is deprecated
  • Check if CLAUDE.md still references it

Best Practice Extraction

  • Analyze recent code for emerging patterns
  • Identify commonly used files as better examples
  • Find frequent issues needing documentation

Detection:

  • Use Grep for common imports/patterns
  • Identify frequently used files
  • Compare against what's documented

Read the full file on GitHub · 160 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. yesterday First seen · 160 lines · 14 tokens per session scan A 248fed4f1978

Subscribe to this mod's changes

audit-claude-md is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 938 once invoked, about $0.0001 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 2026-09-01.