Hookify Rules

If you're using Claude to write code or run shell commands, this adds a pattern matching system that can warn you before you do something questionable. It watches bash commands, file edits, and prompts, then triggers custom rules you define in markdown files with regex patterns. The setup is straightforward: drop .md files in your .claude directory with YAML frontmatter specifying what to watch for (like rm -rf, API keys in .env files, or console.log statements) and what message to show. The action field lets you either warn or outright block operations. It's the kind of safety net that catches the dumb mistakes you make when you're moving fast, like chmod 777 or committing credentials.

skills.sh installs: 5.4K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill hookify-rules --agent claude-code

Installs into .claude/skills of the current project.

Files

Writing Hookify Rules

Overview

ECC evaluates project-local Hookify rules with its built-in Node runtime. No separate Hookify plugin or Python installation is required when ECC hooks are enabled.

Hookify rules are markdown files with YAML frontmatter that define patterns to watch for and messages to show when those patterns match. Rules are stored in .claude/hookify.{rule-name}.local.md files.

Rule File Format

Basic Structure

---
name: rule-identifier
enabled: true
event: bash|file|stop|prompt|all
pattern: regex-pattern-here
---

Message to show Claude when this rule triggers.
Can include markdown formatting, warnings, suggestions, etc.