agent-teams
Agent Teams
Experimental: Agent teams require
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1and may change between Claude Code versions.
BREAKING (Claude Code 2.1.178): The explicit
TeamCreate/TeamDeletetools were removed. Every session now has one implicit team whenCLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1is set — there is nothing to create or tear down. Theteam_nameparameter is still accepted but ignored on the tools that took it (e.g.Agent), so older invocations don't error; omit it in new code. Coordination is otherwise unchanged: spawn teammates with theAgenttool, coordinate withSendMessage, and track work withTaskCreate/TaskList/TaskUpdate.
For the worked setup examples, communication snippets, shutdown procedures, the worktree path-resolution recovery routine, and common dispatch patterns, see REFERENCE.md.
When to Use This Skill
| Use agent teams when... | Use subagents instead when... |
|---|---|
| Multiple agents need to work in parallel | Tasks are sequential and interdependent |
| Ongoing communication between agents is needed | One focused task produces one result |
| Background tasks need progress reporting | Agent output feeds directly into next step |
| Complex workflows benefit from task coordination | Simple, bounded, isolated execution |
| Independent changes to the same codebase (with worktrees) | Context sharing is fine and efficient |