Team Lifecycle v4

Orchestrate multi-agent software development: specification → planning → implementation → testing → review.

Architecture

Skill(skill="team-lifecycle-v4", args="task description")
                    |
         SKILL.md (this file) = Router
                    |
     +--------------+--------------+
     |                             |
  no --role flag              --role <name>
     |                             |
  Coordinator                  Worker
  roles/coordinator/role.md    roles/<name>/role.md
     |
     +-- analyze → dispatch → spawn → STOP
                                 |
                    +--------+---+--------+
                    v        v            v
             [team-worker]  ...    [team-supervisor]
              per-task               resident agent
              lifecycle              message-driven
                                     (woken via SendMessage)

Role Registry

Role	Path	Prefix	Inner Loop
coordinator	roles/coordinator/role.md	—	—
analyst	roles/analyst/role.md	RESEARCH-*	false
writer	roles/writer/role.md	DRAFT-*	true
planner	roles/planner/role.md	PLAN-*	true
executor	roles/executor/role.md	IMPL-*	true
tester	roles/tester/role.md	TEST-*	false
reviewer	roles/reviewer/role.md	REVIEW-, QUALITY-, IMPROVE-*	false
supervisor	roles/supervisor/role.md	CHECKPOINT-*	false

Role Router

Parse $ARGUMENTS:

• Has --role <name> → Read roles/<name>/role.md, execute Phase 2-4
• No --role → @roles/coordinator/role.md, execute entry router

Shared Constants

• Session prefix: TLV4
• Session path: .workflow/.team/TLV4-<slug>-<date>/
• CLI tools: maestro delegate --mode analysis (read-only), maestro delegate --mode write (modifications)
• Message bus: mcp__ccw-tools__team_msg(session_id=<session-id>, ...)

Worker Spawn Template

Coordinator spawns workers using this template:

Agent({
  subagent_type: "team-worker",
  description: "Spawn <role> worker",
  team_name: <team-name>,
  name: "<role>",
  run_in_background: true,
  prompt: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: <team-name>
requirement: <task-description>
inner_loop: <true|false>

## Progress Milestones
session_id: <session-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final SendMessage.

Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})

Supervisor Spawn Template

Supervisor is a resident agent (independent from team-worker). Spawned once during session init, woken via SendMessage for each CHECKPOINT task.

Spawn (Phase 2 — once per session)

Agent({
  subagent_type: "team-supervisor",
  description: "Spawn resident supervisor",
  team_name: <team-name>,
  name: "supervisor",
  run_in_background: true,
  prompt: `## Role Assignment
role: supervisor
role_spec: <skill_root>/roles/supervisor/role.md
session: <session-folder>
session_id: <session-id>
team_name: <team-name>
requirement: <task-description>

## Progress Milestones
session_id: <session-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final SendMessage.

Read role_spec file (@<skill_root>/roles/supervisor/role.md) to load checkpoint definitions.
Init: load baseline context, report ready, go idle.
Wake cycle: coordinator sends checkpoint requests via SendMessage.`
})

Wake (handleSpawnNext — per CHECKPOINT task)

SendMessage({
  type: "message",
  recipient: "supervisor",
  content: `## Checkpoint Request
task_id: <CHECKPOINT-NNN>
scope: [<upstream-task-ids>]
pipeline_progress: <done>/<total> tasks completed`,
  summary: "Checkpoint request: <CHECKPOINT-NNN>"
})

Shutdown (handleComplete)

SendMessage({
  type: "shutdown_request",
  recipient: "supervisor",
  content: "Pipeline complete, shutting down supervisor"
})

User Commands

Command	Action
check / status	View execution status graph
resume / continue	Advance to next step
revise <TASK-ID> [feedback]	Revise specific task
feedback <text>	Inject feedback for revision
recheck	Re-run quality check
improve [dimension]	Auto-improve weakest dimension

Completion Action

When pipeline completes, coordinator presents:

AskUserQuestion({
  questions: [{
    question: "Pipeline complete. What would you like to do?",
    header: "Completion",
    multiSelect: false,
    options: [
      { label: "Archive & Clean (Recommended)", description: "Archive session, clean up team" },
      { label: "Keep Active", description: "Keep session for follow-up work" },
      { label: "Export Results", description: "Export deliverables to target directory" }
    ]
  }]
})

Specs Reference

• specs/pipelines.md — Pipeline definitions and task registry
• specs/quality-gates.md — Quality gate criteria and scoring
• specs/knowledge-transfer.md — Artifact and state transfer protocols

Session Directory

.workflow/.team/TLV4-<slug>-<date>/
├── team-session.json           # Session state + role registry
├── spec/                       # Spec phase outputs
├── plan/                       # Implementation plan + TASK-*.json
├── artifacts/                  # All deliverables
├── wisdom/                     # Cross-task knowledge
├── explorations/               # Shared explore cache
├── discussions/                # Discuss round records
└── .msg/                       # Team message bus

Error Handling

Scenario	Resolution
Unknown command	Error with available command list
Role not found	Error with role registry
CLI tool fails	Worker fallback to direct implementation
Fast-advance conflict	Coordinator reconciles on next callback
Supervisor crash	Respawn with recovery: true, auto-rebuilds from existing reports
Supervisor not ready for CHECKPOINT	Spawn/respawn supervisor, wait for ready, then wake
Completion action fails	Default to Keep Active