Commands Shipped
The full command surface, including the six run commands every run-producing team answers to.
Every call is myteams cookbookteam <command>. Installing the team also registers it as a Claude Code skill, so the same commands are reachable from inside a session as /myagenticteams:cookbookteam <command> — one definition, two front doors.
Commands
| Command | What it does |
|---|---|
| myteams cookbookteam recipe new | Author or formalize a recipe (use --from-code to formalize existing code). |
| myteams cookbookteam recipe build | Translate a recipe into an acceptance contract for the build loop. |
| myteams cookbookteam principle new | Author a principle (statement + practical guidance), grounded in the cookbook. |
| myteams cookbookteam guideline new | Author a guideline (RFC-2119 structured guidance + triggers), grounded in the cookbook. |
| myteams cookbookteam project new | Scaffold a cookbook project (--from-code) and author a recipe per component. |
| myteams cookbookteam project build | Aggregate a project's recipes into one acceptance contract for the build loop. |
| myteams cookbookteam 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 cookbookteam report | Write the run's field report — the facts, plus the driver's own reflection on them. |
| myteams cookbookteam pause | Stop the run at the next safe point, leaving it resumable. |
| myteams cookbookteam resume | Pick a paused run back up where it stopped. |
| myteams cookbookteam log | The run's event stream, as it happened. |
| myteams cookbookteam findings | Everything the run raised, filterable. |
| myteams cookbookteam insights | What the run learned that outlives it. |