Double77x

Agent Hooks — AI skill for Claude Code

AI community

Agent Hooks: A Safety & Workflow Suite for autonomous CLI AI agents.

How to install Agent Hooks

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Double77x/agent-hooks and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Hooks does

Agent Hooks: A Safety & Workflow Suite for autonomous CLI AI agents.

Alternatives in AI

Artifacts Builder — Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web tech 97.5k ★
J Space Cognition Suite V3.7 — J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace r 3k ★
Claudekit — by Carl Rannaberg - Impressive CLI toolkit providing auto-save checkpointing, code quality hooks, specificatio 633 ★

README

Agent Hooks

![TypeScript](https://img.shields.io/badge/TypeScript-007ACC?style=flat-square&logo=typescript&logoColor=white) ![Claude Code](https://img.shields.io/badge/Claude_Code-D97757?style=flat-square) ![Agy CLI](https://img.shields.io/badge/Agy_CLI-4F46E5?style=flat-square) ![Codex](https://img.shields.io/badge/Codex-10A37F?style=flat-square)

An enterprise-grade safety and workflow suite for autonomous AI agents. This repository provides a standardised set of hooks designed to secure the workspace, enforce architectural consistency, and optimise agent reasoning for Claude Code, Agy CLI (Antigravity CLI), and Codex.

Overview

Agent Hooks acts as a deterministic middleware layer between the AI agent and your local system. By intercepting tool calls before and after execution, the system ensures that every action is safe, compliant with project standards, and backed by a clear implementation plan.

The architecture is built on a lean, side-effect-light core. Each hook is a standalone ESM bundle that communicates via strictly formatted JSON on stdout while piping diagnostics to stderr for transparency.

Hook Reference

The following table details the hooks currently available in the suite.

Hook	Event	Utility
Block Dangerous Commands	Pre-Tool Use	Detects and prevents destructive shell operations, such as targeting the root filesystem or executing remote scripts directly.
Protect Secrets	Pre-Tool Use	Shields sensitive files like `.env`, SSH keys, and cloud credentials from being read or exfiltrated by the agent.
Package Manager Enforcement	Pre-Tool U