Hookify rules are simple markdown files that act like a safety checklist for your AI assistant. They watch for certain patterns in commands, file edits, or prompts. When a pattern is found, the rule shows a helpful message or blocks the action. You can create rules to prevent dangerous commands, catch debug code, or enforce best practices. Each rule lives in a .claude/hookify folder and uses easy YAML frontmatter to set its trigger and behavior.
With just a few lines you can add warnings or blockers for things like rm -rf, console.log, or editing secret files. Multiple conditions let you check file paths, command text, or content matches. This gives you fine control over what your AI can and cannot do.
Anyone who uses an AI assistant for coding or system tasks will benefit. You get safer automation and fewer mistakes without needing to watch every action yourself.
Global
mkdir -p ~/.claude/skills/writing-hookify-rulesProject
mkdir -p .claude/skills/writing-hookify-rulesSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Skill Creatoranthropics/skills
Create, test, and improve AI agent skills with easy step-by-step guidance
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly
Openclaw Secure Linux Cloudxixu-me/skills
Secure self-hosting of OpenClaw with private control and SSH tunneling