Commands Shipped
The full command surface, including the six run commands every run-producing team answers to.
Every call is myteams teambuilder <command>. Installing the team also registers it as a Claude Code skill, so the same commands are reachable from inside a session as /myagenticteams:teambuilder <command> — one definition, two front doors.
Commands
| Command | What it does |
|---|---|
| myteams teambuilder create-team | Create a complete, installable team from your intent — a skill-orchestrated dialogue (frame, research, design, approve, materialize, validate, install). |
| myteams teambuilder improve-team | Improve any installed team against its eval fixture — a bounded, interactive run→judge→edit loop. |
| myteams teambuilder report |
The six it gets for free
Because this team declares a report command it produces runs, and every run-producing team answers the same six commands without declaring them. They default to the team's most recent run, so the common case takes no run id at all.
| Command | What it does |
|---|---|
| myteams teambuilder report | Write the run's field report — the facts, plus the driver's own reflection on them. |
| myteams teambuilder pause | Stop the run at the next safe point, leaving it resumable. |
| myteams teambuilder resume | Pick a paused run back up where it stopped. |
| myteams teambuilder log | The run's event stream, as it happened. |
| myteams teambuilder findings | Everything the run raised, filterable. |
| myteams teambuilder insights | What the run learned that outlives it. |