Hooks fire around the agent’s actions — format on write, block a command, log every edit. They are how a team puts its own rules in the loop rather than trusting the model to remember them.
4 in the catalog, most starred first. Stars are popularity, not safety — each card shows its review status.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, slash commands, skills, hooks, subagents, agent teams, and MCP servers. Beginner path to power-user depth. Featured in Awesome Claude Code.
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw