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

Rules To Hooks Auditor

ASecurity

Use when auditing CLAUDE.md / AGENTS.md / rules and migrating probabilistic processes to deterministic hooks — stop, pre-tool-use, post-tool-use, start-session, sub-agent-stop. Triggers on "auditoria rules hooks", "converter rules em hooks", "hooks create skill", "garantias determinísticas", "test enforcement", ".env block", "security hooks", "stop hook tests".

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

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Rules To Hooks Auditor?

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

Security grade badge for Rules To Hooks Auditor
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-rules-to-hooks-auditor/badge)](https://www.skillsdirectory.com/skills/majinmagros-rules-to-hooks-auditor)

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

Download Zip
Files
SKILL.md
---
name: rules-to-hooks-auditor
description: Use when auditing CLAUDE.md / AGENTS.md / rules and migrating probabilistic processes to deterministic hooks — stop, pre-tool-use, post-tool-use, start-session, sub-agent-stop. Triggers on "auditoria rules hooks", "converter rules em hooks", "hooks create skill", "garantias determinísticas", "test enforcement", ".env block", "security hooks", "stop hook tests".
metadata:
  origin: ECC
  source_docs:
    - https://github.com/coleam00/hooks-create-skill (referenciado no vídeo Cole Medin)
    - https://docs.anthropic.com/en/docs/claude-code/hooks
    - https://context7.com/anthropic/claude-code
  skills_used:
    - hookify-rules
    - agent-guardrails
    - criar-skill
---

# Rules to Hooks Auditor — Auditoria Automatizada Rules → Hooks

Converte **regras probabilísticas** (em `CLAUDE.md`, `AGENTS.md`, `.claude/rules/`) em **hooks determinísticos** que garantem execução (exit code 0/2) — baseado no framework do vídeo do Cole Medin "Watch This If Your Coding Agent is Ignoring Your Rules (You Need Hooks)".

## Quando usar (gatilhos concretos)

- "Audite meus rules e me diga quais virar hooks"
- "Converta CLAUDE.md em hooks determinísticos"
- "Meu agente ignora rules — preciso de garantias"
- "Bloquear leitura de .env / comandos perigosos"
- "Garantir que testes rodem no final da conversa"
- "Injetar contexto no start da sessão"
- "Observar ações do agente (post-tool-use logging)"

## Quando NÃO usar

- Criar hooks do zero sem rules base (use `hookify-rules` direto)
- Events não mapeados em rules existentes
- Hooks para ferramentas customizadas não cobertas por rules

## Pipeline (baseado no vídeo + docs oficiais)

### 1. Descoberta & Parsing (Input)
Lê arquivos de rules do projeto:
- `CLAUDE.md` (raiz + path-specific)
- `AGENTS.md` (se existir)
- `.claude/rules/**/*.md` (rules modulares)
- `.claude/settings.json` (hooks já existentes)

Extrai **linhas/seções** que nomeiam **eventos** (processos) vs **judgments** (convenções).

### 2. Classificação (Core Logic)
Para cada regra extraída, classifica:

| Tipo | Exemplo | Ação |
|---|---|---|
| **Judgment/Convention** | "money is integer cents never floats" | **Manter como rule** (encode judgment) |
| **Process/Event** | "after implementing run the tests" | **→ Stop Hook** |
| **Process/Event** | "never read .env file" | **→ PreToolUse Hook** |
| **Process/Event** | "when session starts read decisions.md" | **→ StartSession Hook** |
| **Process/Event** | "before editing routes read rag/citations.py" | **→ PreToolUse Hook (file coupling)** |
| **Process/Event** | "log every command you run" | **→ PostToolUse Hook** |
| **Process/Event** | "never run recursive force delete" | **→ PreToolUse Hook (security)** |
| **Vago/Inútil** | "write clean code" | **Deletar** (modelo já sabe) |

**Heurística**: "Is this naming an event or encoding a judgment?" (pergunta do vídeo)

### 3. Geração de Hook (Output)
Para cada **Process/Event** identificado, gera:

## Exemplo

```text
CLAUDE.md: "after implementing run the tests" (processo) → Stop hook (exit 2 se falha)
"money is integer cents" (judgment) → mantém como rule; "write clean code" → deleta
"never read .env" → PreToolUse block; "log every command" → PostToolUse
```

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 →