メニュー
Use when asked to run or start a Rundown runbook by name (e.g. "run the planning runbook", "start the deploy runbook") and no runbook is active yet. The launcher that resolves a runbook and begins execution. Invocable as /rundown <runbook>.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when stepping through a Rundown runbook that is already active or has just been started, when receiving delegation instructions with a claim token, or when rundown CLI commands appear in step output. For cold-start "run the X runbook" requests with nothing active, the rundown launcher skill starts the runbook first.
Use when orchestrating multi-agent work through rundown delegation, dispatching substeps to child agents, or managing delegation tokens
Use when running the Rundown end-to-end test runbook and reporting structured feedback on the workflow.
Use when implementing a written plan task-by-task — the per-task cycle, commit discipline, and escalation rules that an execute-plan runbook orchestrates around.
Use when running the full plan → review → execute pipeline — write the plan, review it, then implement it behind review and verify gates. The top-level entrypoint that orchestrates writing-plans, plan review, and executing-plans end to end.
Use when converting an existing Claude skill (SKILL.md) into a rundown runbook — distilling the skill's workflow backbone into orchestration steps and artifacts without duplicating the skill's context
| name | rundown |
| description | Use when asked to run or start a Rundown runbook by name (e.g. "run the planning runbook", "start the deploy runbook") and no runbook is active yet. The launcher that resolves a runbook and begins execution. Invocable as /rundown <runbook>. |
The entrypoint for starting a runbook from a cold start. This skill resolves a runbook by name, starts it, and hands off to the execution protocol. It does not contain the protocol itself.
/rundown <runbook> with a runbook name.planning) — invoke that skill;
it starts itself.Resolve the runbook. If the name is ambiguous or you are unsure it exists, list discoverable runbooks:
rundown ls --all
Names support namespace:name (e.g. rundown:planning for the plugin
source). A bare name resolves via the priority chain (project → plugin →
bundled).
Load the execution protocol — before starting. So you are ready to
interpret the first step's output (including a delegation) the moment it
appears, rather than scrambling for the protocol after rundown run has fired:
Skill(skill: "rundown:running-runbooks")
If the runbook contains a - DELEGATE step, also load the delegation
protocol:
Skill(skill: "rundown:delegating-runbooks")
Start it.
rundown run <name>
Capture the run id when you start the runbook: rundown run prints it at
start and every subsequent event carries it as runbookId. You need it for
every mutating command you issue as the orchestrator of a delegation-exposed
run.
Pass inputs if the runbook requires them:
rundown run <name> --input key=value
If rundown run reports missing required inputs, supply them and re-run.
Execute. Follow the loaded
running-runbooks protocol: respond to each
step with rundown pass / rundown fail and trust Rundown for transitions.
On a delegation-exposed run (any runbook with a - DELEGATE step), these
become rundown pass --claim-id <claim_id> / rundown fail --claim-id <claim_id> — the bare
form is for standalone runs only and otherwise refuses with
ACTOR_CONTEXT_REQUIRED.