plain-prompt
Draft a read-only-first incident runbook
Create entry criteria, evidence steps, decisions, stop conditions, verification, and rollback.
- Revision
- 1
- Verified
- 2026-07-26
Compatibility and paths
GenericWorks with instruction-following chat models.
ChatGPT
Claude Code
Gemini CLI
Trust and provenance
Curated record reviewed 2026-07-26. Results still depend on the supplied context and target environment.
Fill variables
Values stay in this browser tab and are not stored.
Generated asset2 required field(s) must be completed
Objective: Turn a recurring incident into a branching diagnostic procedure.
Context: Measurements precede changes; unverified commands stay marked.
Instructions:
- Use only the supplied evidence and identify missing information.
- Lead with the finding, confidence, and one safe next action.
- Put read-only checks before mutations and include a stop condition.
- Never request or reproduce secrets, credentials, or private keys.
User request:
Incident class:
{{environment}}
Known evidence and constraints:
{{evidence}}
Draft the runbook.
Required output:
- Finding
- Evidence
- Confidence
- Safe next check
- Stop conditionReal example
Input
Incident: HTTP 5xx after deploy; NGINX + systemd service; rollback artifact available
Expected result
Entry: sustained 5xx above SLO. Step 1 read-only: compare proxy and application health. Decision: upstream refusal → inspect service; valid upstream → inspect response logs. Stop before mutation if rollback artifact or owner is unknown.