plugins/toolkit/skills/claude-code-agent-teams/SKILL.md
This skill should be used when the user asks to "create an agent team", "run a multi-agent team", "coordinate multiple Claude sessions", "use agent teams", or wants to parallelize work across multiple Claude Code instances.
npx skillsauth add dwmkerr/claude-toolkit claude-code-agent-teamsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Coordinate multiple Claude Code instances working together as a team with shared tasks, inter-agent messaging, and centralized management.
See Agent Teams Guide for the complete reference including use case examples, architecture details, and troubleshooting.
Agent teams are experimental and disabled by default. Enable them:
// settings.json
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
Best for tasks where parallel exploration adds value:
| Use Case | Why Teams Help | |----------|---------------| | Research and review | Multiple angles investigated simultaneously | | New modules or features | Each teammate owns a separate piece | | Debugging competing hypotheses | Test different theories in parallel | | Cross-layer coordination | Frontend, backend, tests each owned by a teammate |
Don't use teams for: sequential tasks, same-file edits, or work with many dependencies. Use a single session or subagents instead.
| | Subagents | Agent Teams | |---|---|---| | Context | Results return to caller | Fully independent | | Communication | Report back only | Message each other directly | | Coordination | Main agent manages all work | Shared task list, self-coordination | | Best for | Focused tasks where only the result matters | Complex work requiring discussion | | Token cost | Lower | Higher (each teammate is a separate instance) |
Use subagents for quick focused workers. Use agent teams when teammates need to share findings, challenge each other, and coordinate independently.
Tell Claude to create a team in natural language:
I'm designing a CLI tool that helps developers track TODO comments across
their codebase. Create an agent team to explore this from different angles: one
teammate on UX, one on technical architecture, one playing devil's advocate.
Claude creates the team, spawns teammates, and coordinates work.
| Mode | Description | Requirements |
|------|-------------|-------------|
| in-process | All teammates in main terminal, Shift+Down to cycle | Any terminal |
| tmux / split panes | Each teammate in its own pane | tmux or iTerm2 |
| auto (default) | Split panes if in tmux, otherwise in-process | — |
Override per-session:
claude --teammate-mode in-process
Or in settings:
{
"teammateMode": "in-process"
}
Create a team with 4 teammates to refactor these modules in parallel.
Use Sonnet for each teammate.
Spawn an architect teammate to refactor the authentication module.
Require plan approval before they make any changes.
The lead reviews plans and approves or rejects with feedback.
Tasks have three states: pending, in progress, completed. Tasks can depend on other tasks. The lead assigns tasks or teammates self-claim. Press Ctrl+T to toggle the task list.
Ask the researcher teammate to shut down
When done:
Clean up the team
Always use the lead to clean up. Shut down all teammates first.
TeammateIdle — runs when a teammate is about to go idle. Exit code 2 sends feedback and keeps them working.TaskCompleted — runs when a task is marked complete. Exit code 2 prevents completion and sends feedback./resume, /rewind don't restore them)| Component | Role | |-----------|------| | Team lead | Main session that creates team, spawns teammates, coordinates | | Teammates | Separate Claude Code instances working on assigned tasks | | Task list | Shared work items that teammates claim and complete | | Mailbox | Messaging system for inter-agent communication |
Storage locations:
~/.claude/teams/{team-name}/config.json~/.claude/tasks/{team-name}/Content adapted from Orchestrate teams of Claude Code sessions (Anthropic documentation).
tools
This skill should be used when the user asks to "create a skill", "write a skill", "build a skill", or wants to add new capabilities to Claude Code. Use when developing SKILL.md files, organizing skill content, or improving existing skills. Do NOT use for plugin development, hook creation, agent creation, or slash command creation — those have dedicated skills.
development
This skill should be used when the user asks to "create a bash script", "write a shell script", or mentions shell scripting conventions.
development
Deep research into technical solutions by searching the web, examining GitHub repos, and gathering evidence. Use when the user explicitly says "use the research skill", "use a research agent", or asks for deep/thorough research into implementation options or technologies.
tools
This skill should be used when the user asks to "set up release please", "configure automated releases", "manage version numbers", "add changelog automation", or mentions release-please, semantic versioning, or monorepo versioning.