← ClaudeAtlas

teamslisted

Organize AI coding agents into teams that collaborate on a shared task. Create teams, add teammates, start them, monitor progress, and collect results. Use this skill when you need parallel agent execution. For single-agent dispatch, use `agents run` instead.
phnx-labs/.agents · ★ 0 · AI & Automation · score 64
Install: claude install-skill phnx-labs/.agents
# Teams Skill ## Build the roster from what is installed Before the first `add`: list the harnesses installed and healthy on this machine (`agents view`), then spread tracks across them — write-heavy tracks on write-probed harnesses, read-only verifier tracks on harnesses whose headless `plan` mode is real (see the capability note below). Harness names in the examples here are anchors, not prescriptions: substitute from your installed set. The bundled `teams-roster-guard` (parallel-teams subrule) blocks a 3rd same-harness teammate on a multi-harness machine unless the brief states `single-harness: <capability reason>` — mixed is the default, monoculture is the documented exception. Organize AI coding agents into teams for parallel collaboration. This skill teaches you how to use the `agents teams` CLI. ## Single Agent vs Teams - **Single agent**: Use `agents run <agent> "prompt" --mode edit` for one-off tasks - **Multiple agents**: Use `agents teams` when you need parallel execution ## Quick Start ```bash # Create a team agents teams create my-feature # Add teammates agents teams add my-feature kimi "Implement the auth middleware" --name auth agents teams add my-feature codex "Build the login UI" --name frontend # Start the team agents teams start my-feature --watch ``` ## Commands | Command | Description | Example | |---------|-------------|---------| | `list` | List your teams, most recent activity first | `agents teams list` | | `create` | Start a new team | `a