Summary
Helps you build event-driven automation for Claude Code using hooks that trigger on tool use, session events, and stop conditions. The real value is in the prompt-based hooks API, which lets you use LLM reasoning to validate tool calls or enforce policies instead of writing brittle bash scripts. You can block dangerous file writes, verify task completion before stopping, or inject project context on session start. The documentation clearly separates the plugin hooks.json format (which needs a wrapper object) from the settings format (which doesn't), something easy to mess up. If you're building plugins or want to add guardrails to your workflow, this covers the full hook lifecycle with practical examples for each event type.
Install to Claude Code
npx -y skills add aiskillstore/marketplace --skill hook-development --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
