Subagent Definitions as Teammates - Claude Code
Reuse custom subagent types as Agent Teams members.
Custom subagent definitions plug directly into Agent Teams. Your "reviewer", "migrator", or "doc writer" subagents become teammates without rewriting them.
What it does
When a team spins up, you can pass a list of subagent definitions for the lead to use as teammates. The lead picks the right agent for each task based on descriptions and tool allowlists. This gives you specialized team compositions - e.g. one coder, one reviewer, one tester - without custom team wiring.
When to use it
- Composing teams of roles you already use as subagents.
- Enforcing tool boundaries within a team (reviewer has no write access).
- Consistency - the same agent definition behaves the same as a teammate or a standalone delegation.
- Sharing team compositions across projects via repo-level definitions.
Gotchas
- A poor mix of roles produces poor team results. Think about coverage.
- Subagents designed for single-task isolation may not fit team workflows that need messaging.
- Frontmatter changes to the subagent definition apply to the team on next spawn.
Official docs: https://code.claude.com/docs/en/agent-teams.md#use-subagent-definitions-for-teammates
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.
Get the weekly deep dive
Tutorials on Claude Code, AI agents, and dev tools - delivered free every week.
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 ToolClaude 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

Nimbalyst: The Open-Source Visual Workspace for Building with Codex and Claude Code
Nimbalyst Demo: A Visual Workspace for Codex + Claude Code with Kanban, Plans, and AI Commits Try it: https://nimbalyst.com/ Star Repo Here: https://github.com/Nimbalyst/nimbalyst This video demos N...

Composio: Connect OpenClaw & Claude Code to 1,000+ Apps via CLI
Composio: Connect AI Agents to 1,000+ Apps via CLI (Gmail, Google Docs/Sheets, Hacker News Workflows) Check out Composio here: http://dashboard.composio.dev/?utm_source=Youtube&utm_channel=0426&utm_...

Claude Code Channels in 8 Minutes
Anthropic has released Channels for Claude Code, enabling external events (CI alerts, production errors, PR comments, Discord/Telegram messages, webhooks, cron jobs, logs, and monitoring signals) to b...
Related Posts

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...

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...
Claude Agent SDK vs Claude Code: When to Build and When to Drive
Claude Agent SDK vs Claude Code explained: same engine, two surfaces. Here is the concrete decision line, plus where Man...
Claude Agent SDK vs LangGraph: Choosing Your Agent Stack in 2026
Claude Agent SDK vs LangGraph head-to-head: architecture, state handling, multi-agent patterns, and real pricing - plus...
Claude Agents vs Skills: Which One Do You Actually Need?
Claude agents vs skills, untangled: agents are workers with their own context window, skills are instructions loaded on...
Claude Code Auto Mode Explained: Permissions Without the Prompts
Auto mode replaces permission prompts with a background safety classifier - here is how the Shift+Tab cycle, hard_deny r...
