Overview Shipped
Every team is a self-contained bundle you install into the registry. Open one to see what it is for, what it can do today, and every specialist and lens inside it.
Teams differ far more than "a group of agents" suggests. Some fan out to a dozen specialists and reconcile the results; some dispatch a single authoring agent against a fixed contract; one runs on a deliberation graph and does not use the objective machinery at all. What they share is the front door, the registry, and the run record.
At a glance
| Team | Engine | For |
|---|---|---|
| devteam | specialist-pipeline | Code review, conformance, planning, and the build loop |
| teambuilder | authoring | Creating new teams and improving existing ones |
| teamtester | builtins only | Running the other teams as subjects, at scale |
| researchteam | specialist-pipeline | Cited, confidence-scored research on a topic |
| cookbookteam | authoring | Recipes, principles and guidelines from source or intent |
| storyteam | specialist-pipeline | Grounded long-form narrative from a gathered corpus |
| socialteam | authoring | Tiered news digests against a fixed interest profile |
| projectteam | roadmap | Decomposing and sequencing a feature |
| brainstormteam | deliberation graph | Four-phase facilitated thinking on any idea |
Lenses per team
devteam dwarfs the rest because code review is the domain that decomposes furthest — there really are a hundred and eighty-seven separable things to look for in a diff. A team with five lenses is not a lesser team; it is a narrower domain.
A note on "specialists"
In a fan-out team a specialist is a real dispatched worker. In an authoring team the specialists are the lenses a single authoring agent has to satisfy — the files say so explicitly, and it would be misleading to count them the same way. teamtester has none at all by design: every one of its commands binds straight to a generic engine builtin, so the judgment lives in the engine's probes and judges rather than in prompts the team ships.
These lists are generated
Every roster below — 47 specialists and 252 lenses, with each one's focus and its verification criteria — is a snapshot built from the team data by a script, not typed by hand. That is the only way a page describing this much surface stays true after the next change to it.