hook-manager
CommunityEnforce filesystem and network policies.
AuthorMassimilianoPili
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill ensures that AI agents only access and modify files and network resources they are explicitly permitted to, preventing unauthorized actions and maintaining system integrity.
Core Features & Use Cases
- Path Ownership Enforcement: Restricts agent write access to designated directories.
- MCP Server Allowlisting: Controls which external services agents can communicate with.
- Use Case: Before an agent begins writing code, this Skill verifies it only writes to the
backend/directory and can only call thegitandrepo-fsMCP servers, ensuring adherence to project structure and security policies.
Quick Start
Use the hook-manager skill to generate hook policies for the current plan.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: hook-manager Download link: https://github.com/MassimilianoPili/agent-framework/archive/main.zip#hook-manager Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.