Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Fixed plist: executable is claude-team not claude-team-mcp
What This Skill Does
MCP server that spawns and manages teams of Claude Code worker sessions inside iTerm2. Each worker gets its own terminal pane and an optional git worktree, and can be assigned a beads issue to work autonomously. Workers run in parallel while the coordinator's context stays clean.
Each worker runs in a real, visible Claude Code session with isolated context and a dedicated git worktree, so parallel work never pollutes the coordinator's context window and can be inspected or taken over at any time.
When to use it
- Fanning out three feature branches to separate workers simultaneously
- Assigning individual beads issues to workers for autonomous parallel implementation
- Monitoring multiple Claude Code agents from a single coordinator terminal
- Waiting for all workers to finish before reviewing and merging their branches
- Sending mid-task corrections to a specific worker without interrupting others
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: implement three separate beads issues in parallel using workers
- 1Calls spawn_workers with three configs, each specifying a bead ID, annotation, and use_worktree true
- 2Each worker creates a git worktree, runs bd show on its assigned issue, and marks it in_progress
- 3Calls wait_idle_workers with mode all and a timeout to block until all three complete
- 4Calls read_worker_logs for each worker to review conversation history and output
- 5Calls close_workers to terminate sessions, then merges or cherry-picks each worker branch
Three beads issues implemented on isolated branches, ready for review and merge to main
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.