What event types are supported by Hookify?

Hookify supports five main event types: bash (terminal commands), file (edits/writes), stop (completion checks), prompt (user input), and all (every event).

Can I block Claude from running dangerous commands?

Yes, by setting the action field to 'block' in the rule's frontmatter, you can prevent Claude from executing matched bash commands or file edits.

Where are Hookify rules stored in a project?

Rules are stored in the .claude/ directory at the root of your project, following the naming convention .claude/hookify.{rule-name}.local.md.

What is a Hookify rule?

A Hookify rule is a markdown file with YAML frontmatter that instructs Claude Code to trigger specific messages or actions when it detects defined patterns in commands, file edits, or user prompts.

How do I test my Hookify regex patterns?

You can test patterns using a Python command: python3 -c "import re; print(re.search(r'your_pattern', 'test text'))" or via online regex testers using the Python flavor.

Hookify Rule Writer

Name: Hookify Rule Writer
Author: nordeim

bynordeim

0•

开发者工具

Simplifies the creation and configuration of custom guardrails and automation rules for Claude Code.

This skill provides comprehensive guidance on authoring Hookify rules to enhance your Claude Code development workflow. It enables users to define custom triggers and messages based on specific events like terminal commands, file edits, or session completions. By leveraging YAML frontmatter and regex patterns, the skill helps developers implement project-specific security blocks, code quality warnings, and process checklists, ensuring that AI-driven coding remains safe, consistent, and compliant with team standards.

主要功能

01Guidance on writing effective Python-compatible regex patterns for code detection

02Standardized file naming and organization conventions within the .claude/ directory

03Template generation for bash, file, stop, and prompt event triggers

04Implementation of 'warn' versus 'block' actions for project safety

05Advanced multi-condition rule configuration using field-based operators

060 GitHub stars

使用场景

01Enforcing code quality by warning against debug statements or unhandled TODOs

02Creating pre-stop checklists to ensure tests and documentation are updated before finishing tasks

03Preventing accidental execution of destructive terminal commands like 'rm -rf'

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nordeim/prompt-engineering writing-rules

For use in Claude.ai and ChatGPT

Download Skill