Prompt library
Prompts to paste into Claude Code, Codex, Cursor or any agent connected to
The Runbook (set one up). They assume the therunbook skill is
installed; with MCP only, they work the same through the MCP tools. Replace
the <…> parts.
Working runs
Section titled “Working runs”Work the next step of a run
Section titled “Work the next step of a run”Work the next agent step of run <exe_…> on The Runbook.
Read the resume brief first and don't redo completed work. Claim exactly oneready step before reading it, do only what its instructions say, and reportit: status for whether you did the work, a verdict for what a check found,outputs matching its schema, a one-paragraph summary, and evidence linkswhere it asks. If you're unsure, lack access, or the step needs judgment,use request-human with a clear question instead of guessing. Then tell mewhat you did and what the brief says next.Work every ready step until the run waits
Section titled “Work every ready step until the run waits”Run the agent loop on The Runbook for run <exe_…> until there is no agentwork left.
Repeat: read the brief, claim one ready step, read it, do it, report it.Heartbeat during long work. When a step is a single command whose exit codeis its result, use `runbook step exec`. Stop as soon as the brief says waitor exit; don't poll or sleep. If you lose a claim, stop work on that step andreconcile from the brief. At the end, list each step you reported with itsstatus, verdict and a one-line summary.Start the right runbook for an alert
Section titled “Start the right runbook for an alert”This alert just fired:
<paste the alert: title, service, labels, link>
Find the runbook in project <project> that fits it (list the runbooks andread the likely ones). Tell me which one you'd run and with which inputs,and why. Don't start it until I confirm; then start it with those inputs andwork its agent steps.Summarize a run
Section titled “Summarize a run”Summarize run <exe_…> on The Runbook for <the incident channel | apostmortem | my manager>.
Read the run and its report. Write: the outcome and how long it took; eachstep in one line with who did it (person or agent) and what they found;every approval with who decided what and their comment; failures, handoffsand retries; and links to the evidence. Quote outputs and summaries asrecorded, mark anything you infer as an inference, and don't include tokens,secrets or personal data.You can also export the report directly: runbook run report <exe> --format md
(or json, junit, pdf).
Explain why a run failed
Section titled “Explain why a run failed”Run <exe_…> on The Runbook failed. Find out why.
Read the run, its failed steps (status, failure type, summary, logs andoutputs) and any catch or finally steps that ran. Tell me the first thingthat went wrong, what happened after it because of it, and whether thefailure came from the work itself (a check that found a problem), therunbook (a wrong expression, a missing input), or the environment (atimeout, access, a lost lease). Suggest what to change, and say whichsuggestions would need a runbook edit and which a rerun.Writing runbooks
Section titled “Writing runbooks”Draft a runbook from an incident doc
Section titled “Draft a runbook from an incident doc”Draft a runbook for The Runbook from this incident write-up:
<paste the postmortem, wiki page or Slack thread>
Turn the steps people actually took into a runbook in project <project>:- one step per action, with an id in snake_case and instructions a newcomer could follow;- `actor: agent` for steps an agent can do with a shell or API, `actor: human` for steps that need judgment or access agents shouldn't have;- `check: true` with declared outputs for anything that measures something;- an approval with named approvers before anything destructive, and `destructive: true` on the destructive step;- inputs for what changes between incidents (service, region, version).
Validate it with `runbook spec validate` until it's clean, save it as adraft, and show me the YAML and what you assumed. Don't publish it.Turn a script or checklist into a runbook
Section titled “Turn a script or checklist into a runbook”Turn <path/to/script.sh | this checklist> into a runbook for The Runbook.
Keep each command that does one thing as its own agent step, so it can runwith `runbook step exec`. Group steps that belong together, add a `finally`step for cleanup the script does in a trap, and make anything the scriptasks a person (a prompt, a "press enter to continue") an approval or ahuman step. Validate it, then show me the runbook and a table of scriptline ranges to step ids.Fix validation errors
Section titled “Fix validation errors”`runbook spec validate <file>` reports errors. Fix them.
For each diagnostic, look up its code in the docs' diagnostics reference,explain the cause in one line, and make the smallest change that fixes itwithout changing what the runbook does. Don't weaken approvals, destructiveflags or auto-decision settings to get past an error; ask me instead.Re-validate until it's clean and show me the diff.Reviewing runbooks
Section titled “Reviewing runbooks”Review a runbook for agent safety
Section titled “Review a runbook for agent safety”Review runbook <id> in project <project> (or <file>) for agent safety. Don'tchange it; report findings.
Check:1. Every step that changes something hard to undo is `destructive: true`, and a human approval with named approvers stands before it.2. No approval that agents may decide (`allow_agents`) or that decides on its own at a timeout (`on_timeout: decide`) can lead to a destructive step, unless that step deliberately sets `allow_auto_decision`.3. Agent steps have clear instructions, declared outputs for what they measure, and evidence where a person will want proof.4. Timeouts, retries and `on_failure` make sense: nothing retries a destructive step, and failures that need a person use `handoff`.5. Nothing relies on `agent.hints` to restrict an agent: hints aren't enforced. Say what access the agent's token should have instead.6. Inputs that end up in commands are typed and constrained (enum, pattern).7. No secrets in the runbook source, vars or `with`.
For each finding give the step id, the risk, and the change you'd make.Review a runbook for people
Section titled “Review a runbook for people”Read runbook <id> as the on-call engineer who will be paged at 3 a.m. andhas never seen it. Report: steps whose instructions are ambiguous, missingcontext (links, dashboards, who to call), approvals whose prompt doesn't saywhat the options do, steps that should remind or escalate and don't, andanything that would leave the run waiting with nobody told. Suggest thewording you'd use. Don't change the runbook.Memory
Section titled “Memory”Save what this run taught us
Section titled “Save what this run taught us”Look back at run <exe_…>. Did we learn anything a future run of thisrunbook would need: an access path, a normal baseline, a known false alarm,a slow dashboard? For each, propose one memory entry (one fact, written soit makes sense without this run) with `--propose`, so a person reviews it.Never save secrets, personal data, or anything that only describes thisrun.