packages/hooks
September 4, 2026 · View on GitHub
English | 中文
Summary
The hooks group lets agent runs use the shell hooks you already wrote for Claude Code or Codex: mount the matching bridge, point it at your existing hooks.json, and those hooks fire at the corresponding moments in agent runs — when a session starts, when a prompt is submitted, before and after a tool runs, or when a run is about to stop. Hooks can block a prompt or tool call with a message the model sees, attach extra context to the conversation, or force the run to continue. Choose this group when existing hook configs should keep working without being rewritten as native plugins; each bridge covers the command-hook subset its reference tool documents. hook-protocol is the shared hook engine both bridges use, so the two dialects behave the same way where their protocols agree.
Table of Contents
Packages
| Package | Role | Shape |
|---|---|---|
hook-protocol | Shared hook engine both bridges use; never configured directly | library |
hooks-claude-code | Run your existing Claude Code hooks.json hooks during agent runs | plugin |
hooks-codex | Run your existing Codex hooks.json hooks during agent runs | plugin |
Related documentation
- Interception extension-points Agent Note — the typed-Decision surface the bridges program against.
- Hook bridges Agent Note — the bridge design and its decision mapping.
- Hook protocol library Agent Note — what the shared library owns and why.
Dev Note
Working context for maintainers — click to expand
None.