| name | maestro-companion |
| disable-model-invocation | false |
| description | Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks. |
| argument-hint | <intent> [-y] |
| allowed-tools | ["Bash","Edit","Glob","Grep","Read","Write","followup_task","interrupt_agent","list_agents","request_user_input","send_message","spawn_agent","spawn_agents_on_csv","wait_agent"] |
| session-mode | run |
| contract | {"discovery":"self-described","consumes":[],"produces":[]} |
| version | 0.5.83 |
Agent timeout: spawn_agent 异步执行且无内置超时 — 除明确短任务外一律 spawn_agent 后立即 wait_agent({ timeout_ms: 3600000 })（上限 1 小时）阻塞等待，绝不依赖 30000 默认值；timed_out: true 且 Agent 未完成时再次 wait_agent 续等，不丢弃。批量场景使用 spawn_agents_on_csv({ max_runtime_seconds: 3600, ... })。
<required_reading>
@/.maestro/workflows/run-mode.md
@/.maestro/workflows/codex-run-mode.md
</required_reading>
If any required file above was not expanded into context by the host, or its content is no longer in context, Read it explicitly before executing any step.
Minimal-run execution channel. Full LLM capability with one bounded Run and evidence appended to `{run_dir}/evidence/companion-log.md`.
Use when:
- Intent is mechanically clear (no design decisions needed; file count irrelevant)
- No typed artifact consumed by downstream steps
- No gate/verdict needed for lifecycle tracking
Lightweight self-check (all must hold):
- Intent specifies a concrete, bounded action with named target (file, function, error message)
- No typed artifact consumed by downstream steps
- No gate/verdict for lifecycle tracking
- Single concern, no multi-phase span
If self-check fails mid-execution, stop and suggest
/maestro-next for re-routing.
$ARGUMENTS — intent text + optional flags.
| Flag | Effect |
|---|
-y | Skip confirmation, execute directly |
Mode detection: intent → execute | empty → request_user_input: request intent text; if still empty → display usage hint and exit
Knowledge utilities (note/log/promote) are available via /maestro-knowledge.
1. Execute mode follows the exact Session identity -> bounded Run lifecycle in `run-mode.md`.
2. Evidence is append-only, non-formal (never enters gates or artifact registry)
3. No automatic multi-step orchestration — the command owns exactly one explicit single-step Session chain
Execute (default)
Linear: resolve Session identity -> dispatch Run -> explore -> confirm -> do -> check -> complete Run -> complete Session when the chain is terminal.
1. Create
Follow the self-start flow in run-mode.md. Negotiate capabilities, then execute the three receipt-chained mutations below. {open_request_id}, {insert_request_id}, and are distinct stable IDs; use the exact and returned by each preceding receipt. Participant and actor are the same authorized identity.
