start-work

name	start-work
description	Execute a Prometheus work plan in Codex with Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.

Claude Code Harness Tool Compatibility

This skill may include examples copied from the OpenCode or Codex harness. In Claude Code, do not call OpenCode/Codex-only tools such as task(...), call_omo_agent(...), spawn_agent(...), background_output(...), wait_agent(...), team_*(...), send_message(...), followup_task(...), or close_agent(...) literally. Translate those examples to Claude Code native tools:

OpenCode / Codex example	Claude Code tool to use
task(subagent_type="explore", ...) / call_omo_agent(...) / spawn_agent(agent_type="explorer", ...)	the Task tool (spawn a subagent of the matching type)
task(subagent_type="plan"/"oracle", ...) / spawn_agent(agent_type="plan"/"reviewer", ...)	the Task tool with the planner/reviewer subagent, or the Skill tool
task(category="...", ...)	the Task tool (general-purpose subagent) or run the work inline
background_output(...) / wait_agent(...)	await the subagent's return value / the system completion notification
team_*(...) / send_message/followup_task/close_agent	run multiple Task subagents and synthesize their results

When translating load_skills=[...], invoke the requested skills with the Skill tool or pass their names in the spawned subagent's prompt. If a code block below conflicts with this section, this section wins.

(superseded) Codex Harness Tool Compatibility

This skill ports the OpenCode /start-work flow onto Codex. Any OpenCode-only tool name in an inherited example must be translated to its Codex equivalent:

OpenCode example	Codex tool to use
task(subagent_type="explore", ...)	spawn_agent(agent_type="explorer", task_name="...", message="...")
task(subagent_type="librarian", ...)	spawn_agent(agent_type="librarian", task_name="...", message="...")
task(subagent_type="plan", ...)	spawn_agent(agent_type="plan", task_name="...", message="...")
task(subagent_type="oracle", ...) for final verification	spawn_agent(agent_type="codex-ultrawork-reviewer", task_name="...", message="...")
task(category="...", ...) for implementation or QA	spawn_agent(agent_type="worker", task_name="...", message="...")
background_output(task_id="...")	wait_agent(...)
dispatchInternalPrompt(...)	the Stop hook emits {"decision":"block","reason":"<prompt>"} automatically; see Continuation
team_*(...)	spawn_agent + send_message + followup_task + wait_agent + close_agent

When translating load_skills=[...], name the skills inside the spawned agent's message. If a code block below conflicts with this section, this section wins.

start-work

Execute a Prometheus work plan until every top-level checkbox is complete. This skill pairs with the Codex Stop / SubagentStop continuation hook in components/start-work-continuation, which re-injects the next turn while .omo/boulder.json says the current codex:<session_id> still has unchecked plan work.

Usage

$start-work [plan-name] [--worktree <absolute-path>]

• plan-name is optional. It may be a full or partial file stem under .omo/plans/.
• --worktree is optional. Use it only when the user explicitly asks to work in a separate git worktree.

Phase 1: Select the plan

1. Read .omo/boulder.json if it exists.
2. List Prometheus plan files under .omo/plans/.
3. If plan-name was provided, select the matching plan.
4. If exactly one active or paused Boulder work exists for this session, resume it.
5. If no active work exists and exactly one plan exists, select it.
6. If multiple plans remain possible, ask one focused selection question.

Phase 2: Create or update Boulder state

Write .omo/boulder.json before implementation starts. Session ids must be prefixed with codex: so the continuation hook can identify its own session.

{
  "schema_version": 2,
  "active_work_id": "<work-id>",
  "works": {
    "<work-id>": {
      "work_id": "<work-id>",
      "active_plan": ".omo/plans/<plan-name>.md",
      "plan_name": "<plan-name>",
      "session_ids": ["codex:<session_id>"],
      "status": "active",
      "worktree_path": null
    }
  }
}

If --worktree is set, verify the path with git worktree list --porcelain or create it with git worktree add <path> <branch-or-HEAD>, then store the absolute path as worktree_path. All edits, commands, tests, and evidence capture must run inside that worktree.

Phase 3: Execute the next checkbox

1. Read the full selected plan.
2. Find the first unchecked column-0 checkbox in ## TODOs or ## Final Verification Wave.
3. Ignore nested checkboxes under acceptance criteria, evidence, and definition-of-done sections.
4. Decompose that checkbox into atomic sub-tasks.
5. Dispatch independent sub-tasks in parallel with spawn_agent; serialize only when one sub-task has a named dependency on another.

Each sub-task message must include:

1. Goal and exact files or directories in scope.
2. Required red test or failing reproduction before production changes.
3. Implementation constraints from the plan and project rules.
4. Automated verification commands to run.
5. One Manual-QA channel: HTTP call, tmux session, browser use, or computer use.
6. Required artifact path and cleanup receipt.

Phase 4: Verify and record evidence

For each checkbox, complete all four gates before marking it done:

1. Plan reread: confirm the checkbox and acceptance criteria.
2. Automated verification: run tests, typecheck, lint, build, or the plan-specific equivalent.
3. Manual-QA channel: capture a real artifact, not a dry-run claim.
4. Cleanup: close temporary processes, tmux sessions, browser contexts, ports, containers, and temp directories.

Append evidence to .omo/start-work/ledger.jsonl using one JSON object per line. Include at least event, plan, task, session_id, commands, artifact, and cleanup fields.

Phase 5: Mark progress

Only after verification passes:

1. Edit the plan checkbox from - [ ] to - [x].
2. Re-read the plan and confirm the remaining count decreased.
3. Append a task-completed ledger entry.
4. Continue with the next checkbox. Do not ask whether to continue.

Completion

When all top-level checkboxes in ## TODOs and ## Final Verification Wave are complete:

1. Run the plan's final verification commands.
2. If worktree mode was used, sync .omo/ state back to the main repo, merge or hand off exactly as requested, and remove the worktree only after successful merge or explicit handoff.
3. Remove or mark the Boulder work as completed.
4. Print an ORCHESTRATION COMPLETE block with the plan path, verification commands, artifacts, and cleanup receipts.

Hard rules

• No production change before a failing test or reproduction exists.
• No --dry-run as completion evidence.
• No tests-only completion claim. A Manual-QA artifact is required.
• No unprefixed session ids in Boulder state. Codex sessions are always codex:<session_id>.
• No stale-memory execution. The plan and ledger are the durable source of truth.