Team Lifecycle V4

What it does

When your agent uses it

• Team lifecycle v4
• Tasks that involve Design patterns

Example prompts

• “team lifecycle v4”
• “/team-lifecycle-v4”

Requirements

• Pre-approved tools (allowed-tools): spawn_agent(*), wait_agent(*), send_message(*), followup_task(*), close_agent(*), list_agents(*), report_agent_job_result(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*), request_user_input(*), mcp__ccw-tools__team_msg(*)

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

1. 1Load state -- Read /tasks.json, filter tasks for current wave
2. 2Skip failed deps -- Mark tasks whose dependencies failed/skipped as skipped
3. 3Build upstream context -- For each task, gather findings from context_from tasks via tasks.json and discoveries/{id}.json
4. 4Separate task types -- Split into regular tasks and CHECKPOINT tasks
5. 5Spawn regular tasks -- For each regular task, call spawn_agent({ agent_type: "team_worker", message: "..." }), collect agent IDs
6. 6Wait -- wait_agent({ timeout_ms: 1800000 }) — apply timeout cascade if timed_out
7. 7Collect results -- Read discoveries/{task_id}.json for each agent, update tasks.json status/findings/error, then close_agent({ target })…
8. 8Execute checkpoints -- For each CHECKPOINT task, followup_task to supervisor, wait_agent, read checkpoint report from artifacts/, parse…
9. 9Handle block -- If verdict is block, prompt user via request_user_input with options: Override / Revise upstream / Abort
10. 10Persist -- Write updated state to /tasks.json

What it can do on your machine

Read from SKILL.md and the folder at commit 07491b0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • spawn_agent(*)
  • wait_agent(*)
  • send_message(*)
  • followup_task(*)
  • close_agent(*)
  • list_agents(*)
  • report_agent_job_result(*)
  • Read(*)
  • Write(*)
  • Edit(*)

  …and 5 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Team Lifecycle V4 loads about 3k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 762 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~57

When it runs · the whole SKILL.md, loaded when a task matches

~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: spawn_agent(*), wait_agent(*), send_message(*), followup_task(*), close_agent(*), list_agents(*), re

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from catlog22/Claude-Code-Workflow at commit 07491b0, republished under its MIT licence (© catlog22). 762 words, ~2,979 tokens.

name

team-lifecycle-v4

description

Full lifecycle team skill with clean architecture. SKILL.md is a universal router — all roles read it. Beat model is coordinator-only. Structure is roles/ + specs/ + templates/. Triggers on "team lifecycle v4".

allowed-tools

spawn_agent(*), wait_agent(*), send_message(*), followup_task(*), close_agent(*), list_agents(*), report_agent_job_result(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*), request_user_input(*), mcp__ccw-tools__team_msg(*)

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 -> wait -> collect
                                 |
                    +--------+---+--------+
                    v        v            v
            spawn_agent    ...     spawn_agent
          (team_worker)         (team_supervisor)
              per-task             resident agent
              lifecycle            followup_task-driven
                    |                     |
                    +-- wait_agent --------+
                              |
                         collect results

spawn_agent({
  agent_type: "team_worker",
  task_name: "<task-id>",
  fork_turns: "none",
  message: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
requirement: <task-description>
inner_loop: <true|false>

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).

## Task Context
task_id: <task-id>
title: <task-title>
description: <task-description>
pipeline_phase: <pipeline-phase>

## Upstream Context
<prev_context>`
})

supervisorId = spawn_agent({
  agent_type: "team_supervisor",
  task_name: "supervisor",
  fork_turns: "none",
  message: `## Role Assignment
role: supervisor
role_spec: <skill_root>/roles/supervisor/role.md
session: <session-folder>
session_id: <session-id>
requirement: <task-description>

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

followup_task({
  target: "supervisor",
  message: `## Checkpoint Request
task_id: <CHECKPOINT-NNN>
scope: [<upstream-task-ids>]
pipeline_progress: <done>/<total> tasks completed`
})
wait_agent({ timeout_ms: 1800000 })  // 30 min — apply timeout cascade if timed_out

close_agent({ target: "supervisor" })

spawn_agent({
  agent_type: "team_worker",
  task_name: "<task-id>",
  fork_turns: "none",
  model: "<model-override>",
  reasoning_effort: "<effort-level>",
  message: "..."
})

// Reconcile session state with actual running agents
const running = list_agents({})
// Compare with tasks.json active_agents
// Reset orphaned tasks (in_progress but agent gone) to pending
// ALSO check supervisor: if supervisor missing but CHECKPOINT tasks pending -> respawn

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

.workflow/.team/TLV4-<date>-<slug>/
├── tasks.json                  # Task state (JSON)
├── discoveries/                # Per-task findings ({task_id}.json)
├── spec/                       # Spec phase outputs
├── plan/                       # Implementation plan
├── artifacts/                  # All deliverables
├── wisdom/                     # Cross-task knowledge
├── explorations/               # Shared explore cache
└── discussions/                # Discuss round records

© catlog22, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 33 other files in .codex/skills/team-lifecycle-v4 of catlog22/Claude-Code-Workflow.

• SKILL.md
• MIGRATION-PLAN.md
• instructions/agent-instruction.md
• roles/analyst/role.md
• roles/coordinator/commands/analyze.md
• roles/coordinator/commands/dispatch.md
• roles/coordinator/commands/monitor.md
• roles/coordinator/role.md
• roles/executor/commands/fix.md
• roles/executor/commands/implement.md
• roles/executor/role.md
• roles/planner/role.md
• roles/reviewer
• … and 21 more

Open the folder on GitHubat commit 07491b0