Develop

Develop Skill

This skill covers the Development stage of the AI-DLC workflow: claiming Tasks, writing code, reporting progress, submitting for verification, and managing sessions for worker observability.

Overview

Developer Agents take Tasks created by PM Agents (via the proposal skill, skill_view("chorus:proposal")) and turn them into working code. Each task follows:

claim --> in_progress --> report work --> self-check AC --> submit for verify --> Admin review

For multi-agent parallel execution, the main agent runs Chorus workers as Hermes delegate_task children, with one Chorus session per worker for observability.

Tools

Task Lifecycle:

Work Reporting:

Acceptance Criteria:

Session (workers check in/out; the Team Lead creates and closes):

Workers: always pass sessionUuid to chorus_update_task and chorus_report_work for attribution. Main agent / Team Lead working a task itself: call these tools without sessionUuid — the main agent uses no session.

Shared tools (checkin, query, comment, search, notifications): see the chorus overview skill (skill_view("chorus:chorus"))

Workflow

Step 1: Check In

chorus_checkin()

Review your persona, current assignments, and pending work counts. In a Hermes session the Chorus Hermes plugin already ran this on the first turn (its pre_llm_call hook injects ## Checkin, ## Spec Mode, and ## Quick Reference); call it again only if you need fresh data.

Step 1.5: Get Your Session (Workers Only)

Skip if you are the main agent or Team Lead.

If you are a worker (a delegate_task child), Chorus sessions are NOT auto-created on Hermes. The Team Lead created one for you and put its UUID in your context (look for a Chorus session UUID: line). Keep it for all task operations. If your context has no session UUID, work without one — do not create a session yourself.

Step 2: Find Work

chorus_get_available_tasks({ projectUuid: "<project-uuid>" })

Or check existing assignments:

chorus_get_my_assignments()

Step 3: Claim a Task

chorus_get_task({ taskUuid: "<task-uuid>" })  # Review first
chorus_claim_task({ taskUuid: "<task-uuid>" })

Check: description, acceptance criteria, priority, story points, related proposal/documents.

Step 4: Gather Context

Each task and proposal includes a commentCount field — use it to decide which entities have discussions worth reading.

1. Read the task and identify dependencies:

   chorus_get_task({ taskUuid: "<task-uuid>" })

   Pay attention to dependsOn (upstream tasks) and commentCount.

2. Read task comments (contains previous work reports, progress, feedback):

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

3. Review upstream dependency tasks — your work likely builds on theirs:

   chorus_get_task({ taskUuid: "<dependency-task-uuid>" })
   chorus_get_comments({ targetType: "task", targetUuid: "<dependency-task-uuid>" })

   Look for: files created, API contracts, interfaces, trade-offs.

4. Read the originating proposal for design intent:

   chorus_get_proposal({ proposalUuid: "<proposal-uuid>", section: "documents" })

   (chorus_get_proposal defaults to section: "basic" — just metadata + a draft index. Pass section: "documents" for the design docs, or section: "full" for docs + task drafts.)

5. Read project documents (PRD, tech design, ADR):

   chorus_get_documents({ projectUuid: "<project-uuid>" })

Document update flow (OpenSpec mode): if the originating proposal description contains a line OpenSpec change slug: <slug>, the project's PRD / tech_design / spec Documents are mirrors of files under openspec/changes/<slug>/. To update such a Document (e.g. clarify an AC, fix a spec scenario before resubmitting), load the openspec-aware skill (skill_view("chorus:openspec-aware")) and follow §3.8: edit the local .md file first, then mirror it — prefer chorus mcp call … --arg-file content=<file> via terminal (see skill_view("chorus:chorus-cli")); when chorus is not on PATH, call the native MCP tool (mcp__chorus__chorus_pm_update_document) directly with content read from the file via read_file. Halt on any error.

⛔ Do not call chorus_pm_update_document with a hand-typed content field in OpenSpec mode. The local file is the source of truth; agent-typed content drifts and burns tokens (openspec-aware §2 Rule 1).

When the LAST task of an OpenSpec idea is verified, the Chorus Hermes plugin appends an archive reminder to the chorus_admin_verify_task result (openspec-aware §3.9) — run openspec archive <slug> --yes, then mirror each emitted openspec/specs/<capability>/spec.md back via §3.8.

Document update flow (spec-lite mode): if the proposal description contains a line Spec-lite: .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/, the project's PRD / tech_design / … Documents are mirrors of the files in that dated folder. To update such a Document, load the spec-lite skill (skill_view("chorus:spec-lite")) and follow its Mirror section: edit the local <type>.md file first, then mirror it via chorus mcp call chorus_pm_update_document "{\"documentUuid\":\"<uuid>\"}" --arg-file content=<file> (recorded documentUuid from the file's frontmatter); when chorus is not on PATH, call mcp__chorus__chorus_pm_update_document directly with content read from the file via read_file. Halt on error. Same ⛔ do-not-hand-type-content rule as OpenSpec. The durable .chorus/specs/<slug>/spec.md is edited in place too but is never mirrored (git history is its record). No archive flow — spec-lite has no CLI/validate/archive; on delivery just set spec.md status: done.

In the no-OpenSpec, no-spec-lite fallback (free-form: no locator line), edit the Document content directly via the existing MCP tool, with no local file step.

Step 5: Start Working

Worker: checkin to the task first:

chorus_session_checkin_task({ sessionUuid: "<session-uuid>", taskUuid: "<task-uuid>" })

Then mark as in-progress:

# Worker:
chorus_update_task({ taskUuid: "<task-uuid>", status: "in_progress", sessionUuid: "<session-uuid>" })

# Main agent:
chorus_update_task({ taskUuid: "<task-uuid>", status: "in_progress" })

Dependency enforcement: If this task has unresolved dependencies (dependsOn tasks not in done or closed), the call will be rejected with detailed blocker info. Use chorus_get_unblocked_tasks to find tasks you can start now.

Step 6: Report Progress

Report periodically with chorus_report_work. Include:

• What was completed
• Files created or modified
• Git commits and PRs
• Current status / remaining work
• Blockers or questions

chorus_report_work({
  taskUuid: "<task-uuid>",
  report: "Progress:\n- Created src/services/auth.service.ts\n- Commit: abc1234\n- Remaining: unit tests",
  sessionUuid: "<session-uuid>"
})

Report with status update when complete:

chorus_report_work({
  taskUuid: "<task-uuid>",
  report: "All implementation complete:\n- Files: ...\n- PR: https://github.com/org/repo/pull/42\n- All tests passing",
  status: "to_verify",
  sessionUuid: "<session-uuid>"
})

Step 7: Self-Check Acceptance Criteria

Before submitting, check structured acceptance criteria:

task = chorus_get_task({ taskUuid: "<task-uuid>" })

# If task.acceptanceCriteriaItems is non-empty:
chorus_report_criteria_self_check({
  taskUuid: "<task-uuid>",
  criteria: [
    { uuid: "<criterion-uuid>", devStatus: "passed", devEvidence: "Unit tests cover this" },
    { uuid: "<criterion-uuid>", devStatus: "passed", devEvidence: "Verified manually" }
  ]
})

For required criteria, keep working until you can self-check as passed. Only use failed for optional criteria that are out of scope.

Step 8: Submit for Verification

Workers — checkout first:

chorus_session_checkout_task({ sessionUuid: "<session-uuid>", taskUuid: "<task-uuid>" })

Then submit:

chorus_submit_for_verify({
  taskUuid: "<task-uuid>",
  summary: "Implemented auth feature:\n- Added login/logout endpoints\n- JWT middleware\n- 95% test coverage\n- All AC self-checked (3/3 passed)"
})

to_verify does NOT unblock downstream tasks — only done (after admin verification) does.

Review Agent: After chorus_submit_for_verify, the Chorus Hermes plugin appends a reminder to the tool result telling you to run the chorus-task-reviewer — an independent, read-only reviewer. You MUST run it yourself (it is NOT auto-launched). Workers skip this: the Team Lead reviews after the worker batch returns. The reviewer runs as a delegate_task child under the read-only guard, so it cannot run terminal; build the evidence bundle first, then delegate. delegate_task blocks until the reviewer finishes. The verdict is the comment the reviewer posts on the task, not the call's return value.

Build the evidence bundle (parent, via terminal; <base> is the branch point, e.g. main):

mkdir -p /tmp/chorus-review/<task-uuid>
git diff <base>...HEAD > /tmp/chorus-review/<task-uuid>/diff.patch
git log --oneline <base>..HEAD > /tmp/chorus-review/<task-uuid>/log.txt
<project test/build command> > /tmp/chorus-review/<task-uuid>/tests.txt 2>&1

Run the task reviewer:

delegate_task(
  goal="[chorus-reviewer:task] Review Chorus task <task-uuid> and post one VERDICT comment.",
  context="[chorus-reviewer:task]\nFirst call skill_view(\"chorus:chorus-task-reviewer\") and follow it.\nTask UUID: <task-uuid>\nProject UUID: <project-uuid>\nMax review rounds: 3\nRepo: <abs repo path>\nEvidence: /tmp/chorus-review/<task-uuid>/diff.patch, /tmp/chorus-review/<task-uuid>/log.txt, /tmp/chorus-review/<task-uuid>/tests.txt",
)

The [chorus-reviewer:task] marker MUST be the first line of context (and should also be in goal) — the plugin uses it to put the child in read-only mode. The proposal and code reviewer examples are in the review skill (skill_view("chorus:review"), Review Strategy).

After the reviewer completes, read its VERDICT:

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

Find THIS round's VERDICT: comment — the one posted after your dispatch, not an older round's — and act on it:

• VERDICT: PASS — All AC verified, no issues. Proceed to admin verification.
• VERDICT: PASS WITH NOTES — All AC verified, minor notes. Proceed to admin verification (notes are non-blocking).
• VERDICT: FAIL — BLOCKERs found. Do NOT verify. Fix the BLOCKERs listed in the reviewer's comment, then resubmit.

If no new VERDICT: comment appears after the reviewer returns, check what it did post. A comment reporting that the round limit was reached, or any other explicit refusal to review, is a deliberate escalation to a human: STOP — do not respawn, do not self-review, do not post a VERDICT of your own. If it posted nothing at all, respawn it 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 task yourself as a read-only pass using the checklist and POST the VERDICT comment. Absence is never a PASS.

Final code-review gateway (after the Idea's LAST task is verified): when the task you just verified is the last task of its idea-rooted proposal, the feature is about to ship — the Chorus Hermes plugin appends a reminder to the chorus_admin_verify_task result to run chorus-code-reviewer (gated by CHORUS_ENABLE_CODE_REVIEWER, default on). Run it yourself as a delegate_task child with the [chorus-reviewer:code] marker (full example in skill_view("chorus:review")), passing the ideaUuid + round number and an evidence bundle covering the whole feature (aggregate diff, log, and test output across all of the idea's tasks). It reviews the Idea's aggregate code change across all its tasks (cross-task integration, architecture, security, regression, feature-level coverage) and posts one VERDICT comment on the idea. PASS / PASS WITH NOTES → ship; FAIL → fix via the quick-dev skill (skill_view("chorus:quick-dev")): chorus_create_tasks with proposalUuid set to the current approved proposal so the fix tasks attach to it — do NOT reopen the verified tasks. Group related small BLOCKERs by default; split only materially large or independently testable fixes. Require AC self-check, independent task review, and admin verification for every fix task. Re-run aggregate review only after every fix is successfully done; a failed or cancelled fix stops the loop and escalates, bounded by CHORUS_MAX_CODE_REVIEW_ROUNDS (env, default 3; 0 = unlimited). Advisory/behavioral, like the other reviewers. Run it before any idea-completion report.

Step 9: Handle Review Feedback

If the reviewer returns FAIL, or the task is reopened after verification:

All acceptance criteria are reset to pending when a task is reopened.

1. Check feedback:

   chorus_get_task({ taskUuid: "<task-uuid>" })
   chorus_get_comments({ targetType: "task", targetUuid: "<task-uuid>" })

2. Fix every BLOCKER listed in the reviewer's FAIL comment.
3. Checkin again, fix issues, report fixes, resubmit.

Step 10: Task Complete

Once Admin verifies (status: done), move to the next available task (back to Step 2).

Step 11: Idea Completion Report (advisory)

If the task you just self-verified was the LAST one of its Idea (every Task across every approved Proposal is now done/closed) and you have document:write, offer to call chorus_create_report. In an interactive session, ask the human in chat (yes/no). In a gateway (Chorus-woken) session or with no human in chat, post a chorus_add_comment on the Idea that @mentions the owner (@[Name](user:<ownerUuid>) from chorus_checkin) asking whether to write the report, then end the turn and act on the reply when woken. The call requires title (a short report title) plus content; content's parameter description carries the three-section template (## Summary / ## Decisions / ## Follow-ups). Skip on decline — the plugin will remind on the next run.