SubagentStart and SubagentStop hooks fire around subagent lifecycles - at spawn and at completion.

What it does

SubagentStart runs when the main agent delegates to a subagent. It receives the subagent definition and the initial task. SubagentStop runs when the subagent finishes. Together they let you track parallel work, enforce concurrency limits, log per-agent metrics, or annotate the returned result before it reaches the main session.

When to use it

Counting active subagents to cap parallelism.
Tagging logs with the subagent name for observability.
Adding project-specific context to every subagent prompt via Start.
Normalizing or sanitizing subagent return values via Stop.

Gotchas

Many subagents running in parallel means these hooks fire a lot. Keep them lightweight.
Start hooks that modify the task too aggressively can confuse the subagent.
Stop hooks that rewrite results hide what the subagent actually said. Log originals.

Official docs: https://code.claude.com/docs/en/hooks.md#subagentstart