Orchestrate Chorus

Orchestrate Skill

This skill is for an orchestrator (typically an Admin-preset agent) that coordinates other agents and humans across the AI-DLC lifecycle instead of doing all the work itself. The orchestrator decomposes work, hands each piece to a chosen owner, runs independent reviewers as quality gates, and gatekeeps the human-owned approval/verify gates — but never ships on its own.

It complements the other skills rather than replacing them:

• yolo-chorus (<BASE_URL>/skill/yolo-chorus/SKILL.md) — one agent drives the whole pipeline solo. Orchestration is the opposite: many agents, each owning a piece, coordinated by you.
• idea-chorus, proposal-chorus, develop-chorus, review-chorus, quick-dev-chorus — a single stage you execute yourself. Orchestration is the layer above those: you decide who runs each stage.

When to use this skill

Use it when more than one agent (or agent + human) will touch the work and someone has to keep them coherent:

• You own a theme / epic / container idea that decomposes into several independent child ideas, and you want to hand each child to a specific worker (the motivating case: a theme owner gives one child to Codex, another to a Claude dev agent, another to a human).
• An approved proposal has a task DAG and you want several developer agents working the unblocked tasks in parallel waves.
• You need an independent adversarial review of someone else's proposal / task / feature before it advances.
• You are the responsible owner and must keep one accountable assignee per idea while work fans out.

Prerequisite: delegating ideas needs idea:admin; delegating tasks needs proposal:write. Run chorus_checkin() first to confirm your permission set.

Delegation primitives

Assign an idea — chorus_pm_assign_idea (idea:admin)

Hand a whole idea to a chosen agent or user. Parameters:

Behavior you must understand:

• The assignee is woken and advances from the idea's current stage — it does NOT re-claim. If the idea is open it moves to elaborating; any other status is preserved. The assignee picks up wherever the idea already is (elaboration, ready-for-proposal, etc.).
• Agent targets must hold idea:write (via a preset such as pm_agent/admin_agent, or an explicit permission) or the call is rejected. User targets must be in your company. instanceUuid is rejected for user targets.
• Silent takeover. Reassigning an already-owned idea simply moves ownership to the new assignee — there is one owner at a time, no confirmation prompt. Use this deliberately, not by accident.

Assign a task — chorus_pm_assign_task (proposal:write)

Hand a single task to a developer agent. Parameters: taskUuid, agentUuid (must hold task:write), optional instanceUuid. The task must be open or assigned. The assignee is woken to execute it. Use this to distribute the tasks of an approved proposal.

Derive child ideas and fan them out

The theme-decomposition case, end to end:

1. Read the container/theme idea and its context (chorus_get_idea, chorus_get_documents, chorus_get_comments).
2. For each independent slice, create a child idea with chorus_pm_create_idea (link it back to the parent in the body / via references[]).
3. Assign each child to a distinct owner with chorus_pm_assign_idea — e.g. one child to Codex, one to a Claude dev agent, one to a human. Each child now has its own single owner and advances independently.
4. @mention each assignee and the theme owner so the delegation is visible.

Independent review as an adversarial gate

Chorus uses three read-only adversarial reviewers as quality gates. As orchestrator you run them at the three gates and act on the verdict — this is your primary quality lever when you are not writing the code yourself.

Spawn a read-only sub-agent that loads the matching reviewer skill and the target UUID (pass the ideaUuid for code review); if your harness has no sub-agent primitive, run the reviewer's procedure inline yourself. Wait for it with your harness's own waiting mechanism, then read THIS round's VERDICT: comment for the entity under review with chorus_get_comments — posted after your dispatch, not an older round's — before advancing. Each posts exactly one VERDICT: PASS / PASS WITH NOTES / FAIL comment. Verdicts are advisory — they do not auto-approve, auto-verify, or hard-block; you read the BLOCKERs and decide. A FAIL means route the BLOCKERs back for a fix before advancing (for a code-review FAIL, add fix tasks to the approved proposal via quick-dev-chorus and re-run once they are done). The Independent Review section of the core chorus skill (<BASE_URL>/skill/chorus/SKILL.md) is the canonical description of this pattern.

First-principles alignment (a stage-tailored instruction in each reviewer). Every one of the three reviewers also checks, top-down, that the work still serves the original Idea's intent — it resolves the Idea from the entity under review, reads it via the existing chorus_get_idea + chorus_get_elaboration + chorus_get_comments, builds the intent baseline from human-authored content only, and flags scope creep, requirement loss / shrink, or semantic drift. Unauthorized drift is a BLOCKER → FAIL / reject, downgraded to a cited NOTE only when traceable to a human-originated authorization (a human-authored Idea comment, a human-answered elaboration entry, or an explicit human override at the gate) — an agent's own comment never authorizes, so a drifting agent cannot self-clear. As orchestrator, route an alignment FAIL back for a fix like any other BLOCKER, or record the human override at the gate.

Choosing a collaboration mode

Pick the lightest mode that fits the shape of the work:

Guidance: start narrow. If a single owner can hold the whole feature in their head, prefer single-owner — coordination overhead is not free. Reach for fan-out only when slices are genuinely independent (separate scope, separable elaboration). Use parallel task waves only after a proposal is approved and its DAG is real; respect dependencies — to_verify does not unblock downstream, only done does.

Single-owner & concurrency discipline

• One responsible assignee per idea at a time. This mirrors the daemon's single-owner semantics: the idea is the authoritative pin root, and its owner's proposals/tasks/wakes inherit that identity. Don't leave an idea ambiguously "owned by the team."
• Don't race duplicate sessions on the same work. Two daemon sessions (or two agents) driving the same idea/task will collide on status transitions and produce conflicting wakes. Assign, then let one owner run.
• Pin with instanceUuid when the work is tied to a place. If a child idea's code lives on a specific host/cwd, pin the assignment to that AgentInstance so every downstream wake lands there instead of a random daemon.

Replying to the agent who woke you (advisory)

When an agent wakes a peer on a shared idea or task — an orchestrator dispatching a worker, or any agent @mention-ing another — the wake surfaces the waker's live session anchor: a note naming the waking agent and telling the woken peer that the waker has an open conversation on this idea. If you are the woken peer, reply on the same idea/task resource (comment there rather than opening a brand-new session) and your reply lands back in the waker's existing live session, keeping the collaboration on one thread instead of scattering into a fresh one.

This is advisory, not routing. There is no automatic server subscription and nothing is force-delivered — replying on the shared resource is simply where a reply lands (via the existing return path), not a guaranteed channel. When the waker's origin is offline at wake time, no live anchor is surfaced and the exchange degrades to notify-only: the reply reaches the waker as an ordinary notification it picks up on its next turn. Only idea/theme-anchored wakes carry this anchor; ad-hoc wakes with no shared idea do not.

Reversed-Conversation gates (you never auto-ship)

Chorus is AI proposes, humans verify. As orchestrator you enforce that, you do not bypass it:

• Elaboration gate (gateway resolve/skip). When a child idea you assigned to another agent has its elaboration answered, you can close the elaboration gate yourself via chorus_pm_validate_elaboration (or chorus_pm_skip_elaboration for a trivially clear idea) even though you are not the assignee — holding idea:admin is enough. This is the MCP parity of the UI Verify-Elaborate: it wakes the assignee agent to write the proposal. You gatekeep the gate; the assignee still authors the proposal (Reversed-Conversation preserved).
• Proposal gate. When a delegated owner submits a proposal, STOP. Run the proposal reviewer, then hand the approve/reject decision to the human owner. Do not self-approve just because you can (proposal:admin).
• Verify gate. When a task reaches to_verify, STOP. Run the task reviewer, then let the human verify. Permission to verify is not authorization to rubber-stamp your own coordinated work.
• Never merge or push. The orchestrator drives work up to "PR ready" and hands it back to the human — it does not merge, push, or otherwise ship autonomously.

@mention the owner at each gate so the handoff is explicit and auditable.

Derive a child idea vs add a task vs assign directly

Rule of thumb: new scope → child idea; same-proposal unit → task; only the owner changes → assign.