Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Claude Md Auditor

ASecurity

Use when auditing CLAUDE.md length and structure — trims, path-specific rules, HTML comments, prompt-for-next-session. Triggers on "claude md auditor", "claude md trim", "claude md path specific rules", "doctor claude", "/doctor".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgorails

Works with

claude codecursorcli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill claude-md-auditor --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claude Md Auditor?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Claude Md Auditor
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-claude-md-auditor/badge)](https://www.skillsdirectory.com/skills/majinmagros-claude-md-auditor)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: claude-md-auditor
description: Use when auditing CLAUDE.md length and structure — trims, path-specific rules, HTML comments, prompt-for-next-session. Triggers on "claude md auditor", "claude md trim", "claude md path specific rules", "doctor claude", "/doctor".
metadata:
  origin: AUTORAL
  source_docs:
    - https://www.youtube.com/watch?v=icM0ewXGvAw (Simon Scrapes - 19 Claude Code Mistakes)
    - https://docs.anthropic.com/en/docs/claude-code/settings
    - https://docs.anthropic.com/en/docs/claude-code/memory
  platforms: [claude-code, opencode, cursor, codex, gemini-cli, hermes, openclaw]
  requires_adapters: [hooks, commands]
---

# Claude.md Auditor — Auditoria Automatizada do CLAUDE.md/AGENTS.md

Auditoria automatizada do **CLAUDE.md/AGENTS.md** - mede linhas/palavras, sugere trims, path-specific rules, HTML comments, prompt-for-next-session. Baseado no vídeo do Simon Scrapes "19 Claude Code Mistakes".

## Quando usar (gatilhos concretos)

- "Claude.md auditor"
- "Claude.md length auditor"
- "Claude.md trim"
- "Claude.md path specific rules"
- "Claude.md html comments"
- "Claude.md prompt for next session"
- "Doctor claude"

## Quando NÃO usar

- General context budget → use `context-budget`
- Strategic compact → use `strategic-compact`

## Contents

| Topic | Reference |
|---|---|
| Problemas 1-5 do pipeline | `references/pipeline-problems.md` |
| Analise de comprimento | `references/pipeline-analysis.md` |
| CLI, hooks, settings patch | `references/cli-hooks.md` |
| Integracao /doctor, validacao | `references/doctor-integration.md` |

## Regra unhobbling (Batch 17f, #77)

80% do system prompt removido sem perda: procure pares conflitantes
("documente conforme apropriado" vs "nao adicione comentarios") e
regras que so faziam sentido para modelos que precisavam de guardrails
para nao errar. Remover atrito > adicionar regra.

## Checklist de Entrega

- [ ] `claude-md-auditor.js` — Core auditor class
- [ ] `cli.js` — CLI commands (audit, trim, add-path-rule, add-prompt-next)
- [ ] `hooks/claude-md-auditor.js` — Stop hook
- [ ] `settings-patch.json` — Settings.json patch
- [ ] Integration with `/doctor` command
- [ ] Testes de integração

---

## Adapters (Por Plataforma)

```
adapters/
├── opencode/
│   ├── hooks/
│   ├── commands/
│   └── README.md
├── cursor/
│   ├── hooks/
│   └── README.md
├── codex/
│   ├── hooks/

## Ponte: regras Claude 5 (leva YouTube rodada 7)

Este auditor mede TAMANHO e estrutura — não semântica de constraints. Para a reescrita das regras (goal+why+done, sem over-triggers/rituais, boundaries answer-vs-action), rode em seguida claude5-prompt-rewrite (7 regras Fable/Opus 5 + scanner regex de anti-padrões + diff para aprovação). Ordem: audite tamanho aqui → reescreva semântica lá.

## Ponte: AGENTS.md-indice + lookup condicional (auditoria semanal 13-18/09)

Quando o AGENTS.md trava o agente (grande demais): vire indice — 1 linha por area apontando para o artefato, com condicao de lookup ("consulte memoria/ apenas ao resolver bug"). Audite aqui o tamanho; o padrao de distribuicao vive em agent-harness-construction (guides-vs-sensors).

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →