Chorus Yolo

Chorus Yolo Skill

Full-auto AI-DLC pipeline. User provides a prompt; agent drives the entire lifecycle: Idea -> Elaboration -> Proposal -> Review -> Execute -> Verify -> Done.

Overview

/chorus-yolo automates the complete AI-DLC workflow. You provide a natural language description of what you want built, and the agent handles everything:

1. Planning -- create project, idea, self-elaboration, proposal with docs & tasks
2. Proposal Review -- proposal-reviewer adversarial loop
3. Execution -- wave-based parallel task dispatch via Kiro subagents
4. Verification -- task-reviewer adversarial loop + admin verify 4.5. Code-Review Gateway -- code-reviewer reviews the Idea's aggregate change before ship (FAIL → add fix tasks → re-run)
5. Report -- completion summary

/chorus-yolo <prompt>
       |
       v
  Project + Idea + Elaboration + Proposal
       |
       v
  Proposal Reviewer (auto, up to maxProposalReviewRounds)
       |
       v
  Admin Approve --> Tasks materialize
       |
       v
  Wave-based subagent execution
       |  (dev subagent + task-reviewer per task)
       v
  Admin Verify each wave --> unblock next
       |
       v
  Code-Review Gateway (auto, up to maxCodeReviewRounds)
       |  PASS --> ship   |   FAIL --> add fix tasks --> re-run
       v
  Done. Report summary.

Escape hatch: Ctrl+C at any time. All created entities (project, idea, proposal, tasks) persist in Chorus. Resume manually via /chorus-develop or /chorus-review.

Prerequisites

The API key needs write + admin on every resource it touches:

Check at startup:

perms = chorus_checkin().agent.permissions
need = { idea: ["write"], proposal: ["write","admin"],
         task: ["write","admin"], project: ["write"] }

for resource, actions in need:
  missing = [a for a in actions if a not in (perms[resource] or [])]
  if missing: ABORT "/chorus-yolo needs {resource}: {missing}. Use an Admin-preset API key."

Input

/chorus-yolo <natural language prompt>
/chorus-yolo <prompt> --project <project-uuid>

• <prompt> -- what you want built (becomes the Idea content). Available as $ARGUMENTS.
• --project <uuid> -- optional; use an existing project instead of creating a new one

Workflow

Phase 1: Planning

Step 1.1: Resolve Project

Parse the arguments for --project <uuid>.

If --project is provided:

chorus_get_project({ projectUuid: "<uuid>" })

Verify it exists and proceed.

If not provided, search for a suitable existing project first:

# 1. Search for projects matching the prompt topic
chorus_search({ query: "<key terms from prompt>", entityTypes: ["project"] })

# 2. Or list recent projects to find a match
chorus_list_projects()

Review the results. If a project clearly matches the user's intent (same topic, active, relevant scope), use it. If no suitable project exists, create a new one:

chorus_admin_create_project({
  name: "<short title derived from prompt>",
  description: "<1-2 sentence summary of the prompt>"
})

Step 1.2: Create Idea

chorus_pm_create_idea({
  projectUuid: "<project-uuid>",
  title: "<concise title derived from prompt>",
  content: "<full user prompt as-is>"
})

Then claim it:

chorus_claim_idea({ ideaUuid: "<idea-uuid>" })

Step 1.3: Self-Elaboration

In /chorus-yolo mode, the agent generates elaboration questions and answers them itself -- no interactive user questions. This preserves an audit trail without interrupting the user.

Self-elaboration is still a loop. If answering your own questions surfaces a new question, contradiction, or gap, loop back to chorus_pm_start_elaboration for another self-answered round before resolving — don't force a resolve over unresolved ambiguity. There is no human gate in YOLO, so the loop exits on your judgment that nothing material is left open (round cap 10). Steps 1–2 are one round; repeat them as needed, then resolve once in Step 3.

1. Generate and submit questions:

   chorus_pm_start_elaboration({
     ideaUuid: "<idea-uuid>",
     depth: "standard",
     questions: [
       {
         id: "q1",
         text: "<question about scope, architecture, etc.>",
         category: "functional",
         options: [
           { id: "a", label: "<option A>" },
           { id: "b", label: "<option B>" }
         ]
       }
       // ... 5-8 questions covering functional, technical_context, scope aspects
     ]
   })
   

2. Answer immediately (agent selects best options based on the prompt):

   chorus_answer_elaboration({
     ideaUuid: "<idea-uuid>",
     roundUuid: "<round-uuid>",
     answers: [
       { questionId: "q1", selectedOptionId: "a", customText: "Rationale: ..." },
       // ...
     ]
   })
   

3. Resolve — in YOLO mode the agent resolves elaboration autonomously, with no human-confirmation gate (the human-confirmation requirement that applies to the interactive /chorus-idea flow is explicitly waived under /chorus-yolo automation):

   chorus_pm_validate_elaboration({
     ideaUuid: "<idea-uuid>"
   })
   

   chorus_pm_validate_elaboration requires idea:admin. /chorus-yolo already mandates an Admin-preset key in Prerequisites, so this is satisfied. To open another self-elaboration round instead of resolving, just call chorus_pm_start_elaboration again.

Step 1.4: Create Proposal

1. Read the spec mode (already computed). The agentSpawn hook (bin/resolve-spec-mode.sh) has already resolved it — do NOT re-derive. Read the ## Spec Mode section: CHORUS_SPEC_MODE=<lite|openspec|off> + a routing note. Act on it: openspec (usable, shows CHORUS_OPENSPEC_ACTIVE=1) → 2a; off → 2b; lite → 2c. If it says the mode cannot be honored (explicit openspec but unusable), halt and surface it — do NOT fall back or enter 2a with no OpenSpec. (No ## Spec Mode? Source the same resolver; /chorus-openspec-aware §1.) This matters because yolo runs unattended.

2. Create the empty proposal container. The description MUST carry the mode's locator line — OpenSpec: OpenSpec change slug: <slug>; spec-lite: Spec-lite: .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/; free-form: none. description is only settable at creation, so decide the slug/dated-path first.

   chorus_pm_create_proposal({
     projectUuid: "<project-uuid>",
     title: "<feature name>",
     description: "<summary>\n\nOpenSpec change slug: <slug>",                          // OpenSpec (2a)
     // description: "<summary>\n\nSpec-lite: .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/", // spec-lite (2c)
     // description: "<summary>",                                                        // free-form (2b)
     inputType: "idea",
     inputUuids: ["<idea-uuid>"]
   })
   

   Then branch:

   2a. OpenSpec mode (CHORUS_OPENSPEC_ACTIVE=1). Follow /chorus-openspec-aware §3 end-to-end:

   • Pick $SLUG, run openspec new change "$SLUG" (§3.1–§3.2).
   • Author proposal.md, design.md, and one specs/<capability>/spec.md per capability locally on disk (§3.3). ADDED Requirements only; per-spec fallback to free-form Markdown if MODIFIED/REMOVED is needed.
   • Define the chorus_check_response helper (§6); prefer chorus mcp call … --arg-file content=<file> for mirrors (§3.4/§3.6) — the bash-wrapper fallback's $API + json_encode_file are only needed when chorus is not on PATH.
   • Mirror each local file via chorus mcp call chorus_pm_add_document_draft … --arg-file content=<file> (§3.6; fallback = "$API" mcp-tool chorus_pm_add_document_draft "$PAYLOAD") — one call per file, with the document type from /chorus-openspec-aware §5.

   ⛔ Do not invoke chorus_pm_add_document_draft / chorus_pm_update_document_draft / chorus_pm_update_document from the MCP harness with a hand-typed content field in this branch. Re-typing the markdown body wastes 20k+ tokens per proposal and breaks byte-equality with the local files. See /chorus-openspec-aware §2 Rule 1.

   Then continue to step 3 (task drafts).

   2b. Free-form mode (resolved mode = free-form). Only when step 1 resolved to free-form — i.e. explicit CHORUS_SPEC_MODE=off (unset never comes here: it resolves to OpenSpec when usable, else spec-lite/2c). Add a tech design document draft directly via MCP, content authored inline:

   chorus_pm_add_document_draft({
     proposalUuid: "<proposal-uuid>",
     type: "tech_design",
     title: "Tech Design: <feature>",
     content: "<markdown tech design covering architecture, data model, API, module contracts>"
   })
   

   2c. spec-lite mode (resolved mode = lite). Load /chorus-spec-lite. Pick $SLUG (a capability). Ensure the durable .chorus/specs/<slug>/spec.md exists (local-only, no ids; use the spec-lite skill's inline durable-spec template) and update it in place. Create this change's dated folder .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/ with its synced Chorus-typed docs (shape = the spec-lite skill's inline dated-folder document template) — prd.md (primary), optional tech_design.md… The description carries the Spec-lite: .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/ locator (step 2). Mirror each dated-folder <type>.md to its persistent Document byte-exact — first time chorus mcp call chorus_pm_add_document_draft "{\"proposalUuid\":\"<uuid>\",\"type\":\"prd\",\"title\":\"PRD: <feature>\"}" --arg-file content=.chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/prd.md, later edits via chorus_pm_update_document against the recorded documentUuid (chorus-api.sh fallback when chorus not on PATH). spec.md is never mirrored. No openspec/changes/ scaffold; no tasks.md. Then continue to step 3.

3. Add task drafts incrementally (use returned draftUuid for dependency chaining). acceptanceCriteriaItems is required on every draft — at least one non-blank criterion, or the call is rejected:

   # First task
   result1 = chorus_pm_add_task_draft({
     proposalUuid: "<proposal-uuid>",
     title: "<module name>",
     description: "<what to build, referencing tech design>",
     priority: "high",
     storyPoints: 3,
     acceptanceCriteriaItems: [
       { description: "<testable criterion>", required: true },
       // ...
     ]
   })
   
   # Second task, depends on first
   chorus_pm_add_task_draft({
     proposalUuid: "<proposal-uuid>",
     title: "<dependent module>",
     description: "...",
     priority: "medium",
     storyPoints: 2,
     acceptanceCriteriaItems: [...],
     dependsOnDraftUuids: ["<result1.draftUuid>"]
   })
   

4. Validate:

   chorus_pm_validate_proposal({ proposalUuid: "<proposal-uuid>" })
   

   Fix any errors, then proceed.

5. Submit:

   chorus_pm_submit_proposal({ proposalUuid: "<proposal-uuid>" })
   

   After this call, the postToolUse hook injects a nudge to spawn the chorus-proposal-reviewer subagent. You MUST spawn it yourself — it is NOT auto-launched — and wait for it to complete before approving.

Reviewer contract (applies to every review gate below)

Every gate in Phases 2, 4 and 4.5 follows the same three steps. They are written once here; the phases below only name their entity and their stage-specific actions.

1. Spawn and wait. Spawn the reviewer as a read-only sub-agent, then wait for it: spawn it with the subagent tool and wait for that call to return. The call's own return value is not the verdict — the verdict is the VERDICT: comment the reviewer posts.
2. Read THIS round's VERDICT. Call chorus_get_comments on the entity and find the VERDICT: comment posted after your dispatch, not an older round's. Do not advance the gate before you have read it.
3. No VERDICT for this round? Check what the reviewer did post:
   • A reported round limit, or any other explicit refusal to review — a deliberate escalation to a human. STOP: do not respawn, do not self-review, do not post a VERDICT of your own.
   • Nothing at all — respawn ONCE, telling it to stay within its turn budget and reserve its last turns for the VERDICT, then apply this same check again to what the retry posts. An explicit refusal from the retry still means STOP; only a second true silence lets you review the entity yourself as a read-only pass and POST the VERDICT, then proceed on what you posted rather than looping forever.

Absence is never a PASS, and a round limit reached by someone else is never yours to clear.

Phase 2: Proposal Review Loop

After chorus_pm_submit_proposal, the postToolUse hook injects a nudge to spawn the chorus-proposal-reviewer. You MUST manually spawn it as a read-only subagent with the subagent tool, then wait for that call to return, then:

1. Read THIS round's VERDICT:

   chorus_get_comments({ targetType: "proposal", targetUuid: "<proposal-uuid>" })
   

   Look for the VERDICT: comment posted after your dispatch — not an older round's. Do not approve or reject before you have read it; the subagent call's own return value is not the verdict.

2. Act on the VERDICT:

   • PASS or PASS WITH NOTES --

     chorus_admin_approve_proposal({
       proposalUuid: "<proposal-uuid>",
       reviewNote: "PASS from reviewer. <brief summary of notes if any>"
     })
     

     Tasks and documents materialize automatically. Proceed to Phase 3.

   • FAIL -- Read the BLOCKERs from the reviewer comment. Then:

     chorus_pm_reject_proposal({
       proposalUuid: "<proposal-uuid>",
       reviewNote: "FAIL from reviewer. Fixing BLOCKERs: <list>"
     })
     

     Revise the drafts (chorus_pm_update_document_draft, chorus_pm_update_task_draft) to address each BLOCKER, then resubmit:

     chorus_pm_submit_proposal({ proposalUuid: "<proposal-uuid>" })
     

     After resubmission, the hook injects the nudge again — spawn the reviewer yourself for Round 2.

3. Max rounds: Loop up to maxProposalReviewRounds (default 3). If exhausted:

   STOP: "Proposal review failed after {maxRounds} rounds.
          Remaining BLOCKERs: <list>. Human review needed.
          Proposal UUID: <uuid>"
   

4. No new VERDICT for this round? Apply step 3 of the Reviewer contract, reviewing the proposal yourself if the reviewer stays silent.

Phase 3: Task Execution (Wave-Based)

After proposal approval, tasks exist in open status. Execute them in dependency-ordered waves using Kiro subagents. If subagent spawning is unavailable, fall back to main agent execution.

Primary: Kiro subagents (parallel)

wave = 1

loop:
  # 1. Find ready tasks
  unblocked = chorus_get_unblocked_tasks({ projectUuid: "<project-uuid>" })

  if no unblocked tasks and all tasks done:
    break  # All complete

  if no unblocked tasks and some tasks not done:
    # Stuck -- tasks failed review and can't proceed
    break with escalation report

  # 2. Spawn a subagent for each unblocked task (Kiro allows up to 4 concurrent).
  #    You have `subagent` in your tools. For each task, dispatch a developer
  #    subagent with the task UUID + project UUID + a sessionUuid, instructing it
  #    to follow the /chorus-develop workflow:
  #      "Your Chorus task UUID: {task.uuid}. Project UUID: {project-uuid}.
  #       Session UUID: {fresh-session-uuid}. Implement the task per its
  #       description and acceptance criteria. Follow /chorus-develop. Read the
  #       task, proposal, and project documents for context."
  #    If more than 4 tasks are unblocked, dispatch in batches of 4.

  # 3. Wait for all subagents to complete
  #    Each subagent follows /chorus-develop:
  #    claim -> in_progress -> develop -> report -> self-check AC -> submit_for_verify
  #    After each submit_for_verify, the main agent's postToolUse hook nudges the
  #    task-reviewer spawn (handled in Phase 4).

  # 4. Proceed to Phase 4 (verification) for this wave
  wave += 1

What each subagent prompt needs:

• Task UUID(s) + Project UUID
• A sessionUuid to pass on chorus_update_task / chorus_report_work
• The instruction to follow the /chorus-develop workflow

Fallback: Main Agent (sequential)

If subagent spawning fails (unavailable, permission denied, or subagents crash repeatedly), fall back to executing tasks sequentially as the main agent:

for each task in unblocked:
  # Follow the /chorus-develop workflow directly as main agent
  chorus_claim_task({ taskUuid: "<task-uuid>" })
  chorus_update_task({ taskUuid: "<task-uuid>", status: "in_progress" })

  # ... implement the task: read context, write code, run tests ...

  chorus_report_work({ taskUuid: "<task-uuid>", report: "..." })
  chorus_report_criteria_self_check({ taskUuid: "<task-uuid>", criteria: [...] })
  chorus_submit_for_verify({ taskUuid: "<task-uuid>", summary: "..." })

  # postToolUse hook injects the task-reviewer nudge — you must spawn it yourself
  # Proceed to Phase 4 verification for this task before moving to next

The fallback is slower (sequential, not parallel) but still completes the pipeline. The postToolUse hook injects reviewer nudges the same way in both modes — you must always spawn the reviewer manually.

Phase 4: Verification

After each wave's subagents complete, verify their tasks:

for each task in wave_tasks:
  # 1. Check task status
  task = chorus_get_task({ taskUuid: "<task-uuid>" })

  if task.status != "to_verify":
    # Subagent may have failed; skip or handle
    continue

  # 2. Spawn the chorus-task-reviewer subagent (hook nudged it — you must spawn it
  #    yourself) and wait for the `subagent` call to return.
  #    Prompt: "Review task <task-uuid>. Round: N."

  # 3. Read THIS round's task-reviewer VERDICT — the comment posted after your
  #    dispatch, not an older round's. Do not verify or reopen before you have it;
  #    the `subagent` call's own return value is not the verdict.
  comments = chorus_get_comments({ targetType: "task", targetUuid: "<task-uuid>" })

  # 4. Act on VERDICT — three possible outcomes:
  if VERDICT is "PASS":
    # All AC verified, no issues. Mark AC and verify.
    chorus_mark_acceptance_criteria({
      taskUuid: "<task-uuid>",
      criteria: [
        { uuid: "<ac-uuid>", status: "passed", evidence: "<from reviewer>" },
        // ...
      ]
    })
    chorus_admin_verify_task({ taskUuid: "<task-uuid>" })
    # Task is now "done" -- unblocks dependents

  if VERDICT is "PASS WITH NOTES":
    # All AC verified, minor non-blocking notes. Still mark AC and verify.
    chorus_mark_acceptance_criteria({ ... })
    chorus_admin_verify_task({ taskUuid: "<task-uuid>" })

  if VERDICT is "FAIL":
    # BLOCKERs found. Do NOT verify. Reopen for rework.
    chorus_admin_reopen_task({ taskUuid: "<task-uuid>" })
    # Task returns to "open", will be picked up in next wave

After verifying all tasks in the wave, return to Phase 3 to check for newly unblocked tasks.

Max rounds per task: Tracked by maxTaskReviewRounds (default 3). If a task has been reopened maxRounds times, skip it and flag for human escalation:

ESCALATE: "Task '{title}' failed review after {maxRounds} rounds.
           Last BLOCKERs: <list>. Manual intervention needed.
           Task UUID: <uuid>"

Continue with remaining tasks -- do not halt the entire pipeline for one stuck task.

No new VERDICT for this round? Apply step 3 of the Reviewer contract, reviewing the task yourself if the reviewer stays silent.

Phase 4.5: Code-Review Gateway (mandatory pre-ship)

Once every task of the idea's proposal is verified (done) — i.e. Phase 3 finds no more unblocked tasks and all are terminal — run the final ship-time code-review gateway before declaring the Idea done and before the Phase 5b completion report. After the last task is verified, the postToolUse hook injects a reminder to spawn the code-reviewer; you MUST spawn it yourself, wait for the subagent call to return, then read THIS round's VERDICT comment on the idea and act on what it says.

# Spawn the chorus-code-reviewer subagent for the IDEA (not a task). Determine the
# round number by reading prior code-review VERDICT comments on the idea.
#   Prompt: "Review the aggregate code for idea <idea-uuid>. Round: N."

# Wait for the `subagent` call to return, then read THIS round's VERDICT on the idea
comments = chorus_get_comments({ targetType: "idea", targetUuid: "<idea-uuid>" })
# Find the "VERDICT:" comment posted after your dispatch, not an older round's.
# Do not declare the feature shippable before you have read it.

Act on the VERDICT:

• PASS / PASS WITH NOTES — the feature is cleared to ship. Proceed to Phase 5 / 5b.
• FAIL — do NOT ship. Read the BLOCKERs, then fix them via the quick-dev workflow (/chorus-quick-dev): call chorus_create_tasks with proposalUuid set to the current approved proposal so the fix tasks attach to it — do not reopen the already-verified tasks. Group related small BLOCKERs into one cohesive task by default; split only materially large or independently testable fixes. Drive every fix task through Phase 3 → Phase 4, including AC self-check, independent task review, and admin verification. Re-spawn the code-reviewer only after every fix task is successfully done; a failed or cancelled fix task, stop the automatic loop and escalate. Loop bounded by maxCodeReviewRounds (default 3; 0 = unlimited).

# Max rounds escalation
ESCALATE: "Idea '<title>' failed code review after {maxCodeReviewRounds} rounds.
           Last BLOCKERs: <list>. Manual intervention needed. Idea UUID: <uuid>"

No new VERDICT for this round? Apply step 3 of the Reviewer contract, reviewing the idea's aggregate change yourself if the reviewer stays silent.

The code-review gateway is behavioral, consistent with the proposal/task reviewers: its verdict is advisory and does not change the Idea's stored status. The /chorus-yolo orchestrator honors it — PASS to ship, FAIL to loop. It runs before the completion report so the report is never written for a feature with an outstanding FAIL.

Phase 5: Report

After all waves complete, output a markdown summary:

## /chorus-yolo Complete

**Project:** <project-name> (<project-uuid>)
**Proposal:** <proposal-title> (<proposal-uuid>)
**Idea:** <idea-title> (<idea-uuid>)

### Tasks
| Task | Status | Review Rounds |
|------|--------|---------------|
| <title> | done | 1 |
| <title> | done | 2 |
| <title> | ESCALATED | 3 (max) |

### Summary
- Total tasks: N
- Completed: X / N
- Escalated: Y (need human review)
- Waves executed: W

Phase 5b: Idea Completion Report (mandatory)

A successful /chorus-yolo run always finishes the Idea — call chorus_create_report once with proposalUuid set to the last verified proposal. The call requires title (a short report title) plus content; content's parameter description carries the three-section template (## Summary / ## Decisions / ## Follow-ups); follow it. Surface the returned documentUuid in the Phase 5 summary. Skipping is a protocol violation.

Order: the completion report is written only after the Phase 4.5 code-review gateway returns PASS / PASS WITH NOTES. Never write it while a code-review FAIL is outstanding — the report is a ship-time summary, and the gateway is what clears the feature to ship.

Error Handling

Tips

• Keep the initial prompt detailed -- the more context you provide, the better the auto-generated proposal quality
• The proposal-reviewer is your quality gate -- if it keeps FAILing, the prompt may be too vague
• Watch the wave count -- if tasks keep getting reopened, consider Ctrl+C and manually reviewing the feedback
• All audit trail is preserved: elaboration Q&A, reviewer VERDICTs, work reports. Check Chorus UI for full history
• For small/simple tasks, consider /chorus-quick-dev instead -- it skips the Idea->Proposal overhead
• Subagents share your API key; ensure it has the permissions listed in Prerequisites before starting

Next

• To manually review proposals: /chorus-review
• To manually develop tasks: /chorus-develop
• To create quick standalone tasks: /chorus-quick-dev
• For platform overview: see the chorus steering doc.