Can I prevent Claude from running dangerous commands?

Yes, by setting the action field to 'block' in the rule's frontmatter, you can prevent Claude from executing commands or file edits that match your defined regex patterns.

Where should Hookify rules be stored?

Rules must be placed in the .claude/ directory of your project root and follow the naming convention hookify.{rule-name}.local.md.

Do I need to restart Claude to apply new rules?

No, Hookify rules are read dynamically. Any changes to your .local.md files take effect immediately upon the next tool use or event trigger.

What is a Hookify rule in Claude Code?

A Hookify rule is a markdown file containing YAML frontmatter that defines specific patterns to watch for. When a pattern is matched during a bash command or file edit, Claude displays a custom message or blocks the action.

Hookify Rule Identifier

Name: Hookify Rule Identifier
Author: Microck

byMicrock

•

110

•

Security & Testing

Guides the creation and configuration of Hookify rules to enforce project guardrails and automated feedback within Claude Code.

The Hookify Rule Identifier skill provides specialized guidance for creating custom 'Hookify' rules—markdown-based configurations that allow developers to monitor, warn, or block specific actions taken by Claude. By defining YAML frontmatter and regex patterns, users can set up automated triggers for bash commands, file edits, and completion events. This skill is essential for maintaining project security, enforcing coding standards, and creating interactive checklists that streamline the autonomous development workflow.

Key Features

01Guidance on local file organization and .gitignore best practices

02Step-by-step YAML frontmatter configuration for rule files

03Regex pattern writing for bash, file, and prompt event triggers

04Advanced multi-condition logic with operators like regex_match and contains

05Instructional templates for warning and blocking dangerous operations

06110 GitHub stars

Use Cases

01Creating automated completion checklists that trigger when Claude attempts to finish a task

02Preventing the accidental execution of destructive shell commands like 'rm -rf'

03Flagging sensitive data or debug logs (e.g., console.log) before they are committed

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microck/ordinary-claude-skills rule-identifier

For use in Claude.ai and ChatGPT

Download Skill