Where should I store my Hookify rule files?

Rules must be stored in the .claude/ directory of your project root using the naming format .claude/hookify.{rule-name}.local.md.

What are Hookify rules?

Hookify rules are markdown files with YAML frontmatter that define specific patterns for Claude to watch, triggering customized messages or blocking actions when those patterns match.

What regex engine does the pattern matching use?

The rule identifier uses Python regex syntax, allowing for complex pattern matching including literal escapes and common metacharacters like \s, \d, and wildcards.

Do I need to restart the CLI to apply rule changes?

No, Hookify rules are read dynamically and changes take effect immediately on the next tool use (Bash, File, etc.) after the rule file is saved.

Can Hookify block Claude from performing dangerous actions?

Yes, by setting the action field to 'block' in the YAML frontmatter, you can prevent the execution of matching Bash commands or file edits.

Hookify Rule Assistant

Name: Hookify Rule Assistant
Author: Activer007

byActiver007

0•

开发者工具

Automates the creation and management of custom project guardrails and workflow rules for Claude Code using the Hookify framework.

This skill empowers developers to define specialized patterns and behaviors that Claude monitors during a session, enabling automated warnings for dangerous terminal commands, enforcement of coding standards during file edits, and mandatory completion checklists. By leveraging YAML frontmatter and regex patterns within local markdown files, it provides a flexible system for preventing common errors—such as accidental data deletion or leaking sensitive environment variables—while ensuring project-specific best practices are followed consistently.

主要功能

01Multi-event triggering for Bash commands, file edits, and session completion

02Dynamic rule loading from local .claude configuration files

030 GitHub stars

04Advanced regex pattern matching for precise command and code detection

05Customizable warning and blocking actions to enforce project safety

06Conditional logic based on file paths, new text, and command inputs

使用场景

01Blocking the commit of debug statements or sensitive API keys in specific file types

02Preventing accidental execution of destructive commands like rm -rf in production environments

03Enforcing completion checklists to ensure tests are run and documentation is updated before stopping

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add activer007/ordinary-claude-skills rule-identifier

For use in Claude.ai and ChatGPT

Download Skill