Can I block Claude from performing certain actions?

Yes, by setting the action field to 'block' in the rule's frontmatter, you can prevent specific operations from being executed when a pattern is matched.

What are Hookify rules?

Hookify rules are markdown files with YAML frontmatter that define specific patterns for Claude to watch for. When a pattern matches a bash command, file edit, or prompt, Hookify triggers a message or blocks the action.

Where should Hookify rules be stored?

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

How do I test my Hookify regex patterns?

You can test patterns using the Python re module in your terminal or via online tools like regex101.com using the Python flavor.

What event types does Hookify support?

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

Hookify Rule Architect

Name: Hookify Rule Architect
Author: jackzerby

byjackzerby

0•

开发者工具

Standardizes agent behavior by creating and configuring custom Hookify rules for automated code review and command safety.

Hookify Rule Architect provides specialized guidance for creating and managing Hookify rules within the Claude environment. It empowers users to define custom triggers for bash commands, file edits, and session completion, ensuring that Claude adheres to project-specific safety protocols, coding standards, and operational checklists. By using markdown-based rules with YAML frontmatter, it allows for sophisticated regex matching and multi-condition logic to prevent errors and enforce best practices in real-time.

主要功能

01Real-time file edit validation for detecting debug code or sensitive information

02Seamless integration via project-local markdown configuration files

03Custom event triggers for session stops and user prompts

04Advanced multi-condition logic using regex and substring operators

050 GitHub stars

06Automated Bash command monitoring to prevent dangerous operations like 'rm -rf'

使用场景

01Blocking high-risk terminal commands in sensitive project directories

02Preventing accidental commits of console logs or API keys to production environments

03Enforcing a mandatory deployment checklist before the agent finishes a task

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jackzerby/musicscheduler writing-rules

For use in Claude.ai and ChatGPT

主要功能

01Real-time file edit validation for detecting debug code or sensitive information

02Seamless integration via project-local markdown configuration files

03Custom event triggers for session stops and user prompts

04Advanced multi-condition logic using regex and substring operators

050 GitHub stars

06Automated Bash command monitoring to prevent dangerous operations like 'rm -rf'

使用场景

01Blocking high-risk terminal commands in sensitive project directories

02Preventing accidental commits of console logs or API keys to production environments

03Enforcing a mandatory deployment checklist before the agent finishes a task

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jackzerby/musicscheduler writing-rules

For use in Claude.ai and ChatGPT