SubagentStart and SubagentStop Hooks - Claude Code
Fire when subagents spawn and finish.
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
Technical content at the intersection of AI and development. Building with AI agents, Claude Code, and modern dev tools - then showing you exactly how it works.
Was this helpful?
Related Guides
Related Tools
Claude Code
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory...
View ToolCodeburn
Interactive TUI dashboard that shows exactly where your Claude Code and Cursor tokens are going, in real time.
View Tool
Claude Opus 4.7
Anthropic's flagship reasoning model. Best-in-class for coding, long-context analysis, and agentic workflows. 1M token c...
View ToolConductor
Mac app for running parallel Claude Code, Codex, and Cursor agents in isolated workspaces. Watch every agent work at onc...
View ToolRelated Videos
Generate Videos in Codex + Claude Code with This...
Check out HeyGen! https://heygen.1stcollab.com/developersdigest The video introduces HeyGen, an AI video generation platform with a rich API and a CLI that lets developers create, fetch, and manipula...
10x Design in Claude Code and Codex
Try Higgsfield: https://higgsfield.ai/s/higgsfield-general-campaign-developersdigest-juDMTi AI coding agents can build entire websites in minutes, but the default results often still look generic and...
Self Improving Applications with Claude Code & Codex
Build a Self‑Improving Next.js App: Supabase + Vercel Eve + GitHub Issues + Agent Loops Check out Supabase: https://supabase.plug.dev/1wWOTGS The video demonstrates how to build and deploy a self-im...
Related Posts
Claude Outages Are a Workflow Design Problem
Claude outages and 529 overloads expose whether your AI coding workflow has checkpoints, receipts, model-switch paths, a...
Claude Opus 4.8 Is an Agent Honesty Release
Claude Opus 4.8 looks like a benchmark bump, but the developer story is better honesty, dynamic workflows, and effort co...
Hookyard Shows Why Claude Code Hooks Need a Package Manager
Claude Code hooks are powerful, but discovery and install still feel like manual JSON surgery. The Hookyard prototype sh...
Anthropic Sonnet 4.5 in Claude Code
Anthropic's Claude Sonnet 4.5 isn't just another model increment. The company claims they've observed it maintaining foc...
Make Your Coding Agents Talk: Voice Summaries with the Rime CLI
The Rime CLI streams natural-sounding text-to-speech straight from your terminal, so Claude Code, Codex, Devin, and Open...
How to Make Claude Code 10x Better at Design: Image and Video Assets From the Agent Loop
Claude Code and Codex can build a website in minutes, but the result often looks generic and obviously AI-generated. Hig...
