CLAUDE CODE

Fires on tool execution errors for logging, alerting, and retry.

Fires when a permission dialog appears. Auto-approve or auto-deny.

Fires when auto mode or a rule denies an action.

Fire when subagents spawn and finish.

Fire on task lifecycle events.

Fires when Claude finishes responding. Can prevent the stop.

Fires when watched files change on disk.

Fire when settings or CLAUDE.md files change during a session.

Fire before and after context compaction.

Fires when an MCP server requests input from the user.

Run shell scripts on events with environment variable passing.

Use Claude itself to handle hook logic instead of shell scripts.

Spawn subagents to handle complex hook logic.

Run hooks in the background without blocking the session.

Connect external tools and data sources via the open MCP standard.

Local, project, user, and plugin-level MCP configurations.

Deferred tool loading reduces context overhead for large MCP suites.

Pre-configured or dynamic OAuth for remote MCP servers.

Reference and read resources exposed by MCP servers.

Execute MCP prompts as commands via the slash menu.