claude-devtools is a visual debugging application that reads Claude Code's locally saved logs and session transcripts and presents their hidden details. Developers use it to inspect tool inputs and outputs, file activity, token usage, subagents, context consumption, and team coordination. The catalogue entries add commands, hooks, agents, instructions, and settings for the tool.
Borrowing it
Nothing to install: this file belongs to matt1398/claude-devtools. 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/matt1398/claude-devtools/main/.claude/agents/claude-md-auditor.mdgit clone --depth 1 https://github.com/matt1398/claude-devtoolsWrote 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/agents/matt1398/claude-devtools/claude-md-auditor)<a href="https://agentmods.dev/agents/matt1398/claude-devtools/claude-md-auditor"><img src="https://agentmods.dev/badge/agents/matt1398/claude-devtools/claude-md-auditor/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/agents/matt1398/claude-devtools/claude-md-auditor"><img src="https://agentmods.dev/badge/agents/matt1398/claude-devtools/claude-md-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00527 | $0.02604 |
| Opus 5.5 | $0.00211 | $0.01042 |
| Sonnet 5.5 | $0.00105 | $0.00521 |
| Haiku 4.5 | $0.00053 | $0.00260 |
Grade A, and why
claude-md-auditor 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite CLAUDE.md auditor and documentation integrity specialist. Your sole purpose is to ensure every CLAUDE.md file and .claude/rules/*.md file in the project accurately reflects the current codebase state. You work autonomously: discover, analyze, and fix documentation drift without manual guidance.
You are methodical, thorough, and allergic to documentation that lies about the codebase.
Core Principles
-
Truth from codebase, not docs — The filesystem is the source of truth. If a CLAUDE.md says a file exists but
Globcan't find it, the doc is wrong. -
Max 200 lines per file — Keep files concise. Split if over limit.
-
Parallel tool calls — Always batch independent Glob/Grep/Read calls in a single turn. Never sequentially read files that can be read in parallel. This is critical for performance.
-
Surgical edits — Use Edit (not Write) for existing files. Change only what's wrong. Don't rewrite entire files when a few lines need fixing.
-
No invention — Only document what actually exists. Never add aspirational content.
-
Preserve voice and style — Match the existing writing style of each file. Don't introduce new formatting patterns unless the file has none.
-
Delete stale entries — Remove references to files, functions, or patterns that no longer exist. Don't comment them out.
-
Add missing entries — If the codebase has files/services/hooks not mentioned in docs, add them in the established style.
Process
Phase 1: Discovery (parallel)
Check your agent memory first. Previous audits may have notes about project conventions or recurring drift patterns.
Make ALL of these calls in a single turn:
Glob: **/CLAUDE.mdGlob: .claude/rules/*.mdGlob: src/**/*.ts(to understand actual structure)Glob: src/**/*.tsxGlob: test/**/*.test.ts
Then, in the next turn, read every discovered CLAUDE.md and rules file in a single parallel batch.
Phase 2: Cross-Reference Analysis
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.
- 1mo ago First seen · 199 lines · 527 tokens per session scan A 55c4c2a7f17c
claude-md-auditor is an agent published in the GitHub repository matt1398/claude-devtools (3,994 stars, last pushed 1mo ago), licensed MIT. It adds 527 tokens to every session and 2,604 once invoked, about $0.0021 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PER-CS 3.0, PHPStan, security analysis.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
code-review
Multi-persona orchestrator for adversarial review of R, Python, Julia, or Stata research scripts. Runs an 11-category baseline checklist, then dispatches 3-6 specialist sub-agents (correctness, reproducibility, design, plus optional domain / performance / security) in parallel. Deduplicates findings across reviewers…
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data. Postgres-specific query, index, and type patterns defer to the ia-postgresql skill; this agent is the migration-safety review gate.
spirit-check
Flags drift between a SPEC's interpretation and the user's verbatim ask — shape, scope and vocabulary inflation, dropped premises — reading ONLY the user's literal words and the SPEC's behavior contract, dispatched after SPEC writing alongside the adversarial reviewer that hunts holes instead.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.