Incident Response taste — ChatGPT prompt: what it does
The Incident Response taste prompt for ChatGPT sets out how a calm on-call engineer can handle incidents. It calls for early declaration and coordinated response before the root cause is known.
CC0-1.0 ★ 178,201 updated 2026-10-24
Open on GitHubWhat Incident Response taste does
The prompt lays out an incident process: declare incidents early, assign a commander, keep decisions in a dedicated channel, and record events as they happen with UTC timestamps. Its priority is reducing impact first, such as rolling back a change or disabling a feature flag, then investigating the cause.
For larger incidents, it separates coordination from communications and calls for regular status-page updates. Shift handoffs include a written account of the current state and next steps. The prompt recommends a blameless review for every SEV1 and SEV2 within five working days. It also covers alert thresholds, postmortem actions, and on-call rotations.
What it helps with
- declare an incident before the root cause is known
- assign a commander and separate communications lead
- record incident events with UTC timestamps
- hand off an open incident with written next steps
- turn postmortem findings into owned, dated actions
Example prompts for the agent
- Use Incident Response taste to draft a response plan for this outage.
- Help assign roles and track events for a SEV2 incident.
- Write a status-page update and a handoff note for the next on-call shift.
How to install Incident Response taste
How to use
Paste the text at the start of a chat or into project instructions
Manually: put the files in place
.claude/commands/prompts.csv.mdQuestions about Incident Response taste
How do I install Incident Response taste in ChatGPT?
Use it as a prompt by adding its text to a ChatGPT conversation. For Claude Code, the listed file is .claude/commands/prompts.csv.md.
What does Incident Response taste do?
It describes an incident response process, including declaration, coordination, mitigation, shift handoff, and postmortems. It also sets out guidance for alerts and status updates.
When should SEV1 and SEV2 incidents get a postmortem?
The prompt calls for a blameless postmortem for every SEV1 and SEV2 within five working days.
Source text
prompts.csv · CC0-1.0
# Incident Response taste of a calm on-call engineer - Declare an incident early and downgrade it later; a false alarm costs far less than a slow start. Confidence: 0.90 - Use a small, fixed severity scale (SEV1 to SEV4) with written, customer-impact-based definitions everyone can check in seconds. Confidence: 0.90 - Assign one incident commander who coordinates and does not debug, plus a separate communications lead for bigger incidents. Confidence: 0.90 - Open a dedicated incident channel per incident with a predictable name, and keep all decisions in it rather than in DMs. Confidence: 0.85 - Keep a running timeline with timestamps in UTC from the first alert, written as events happen instead of reconstructed later. Confidence: 0.85 - Mitigate first and find the root cause later: roll back, fail over or turn off the feature flag before digging into why. Confidence: 0.95 - Make rollback a one-command, well-practiced action that any on-call engineer can run without approval during an incident. Confidence: 0.85 - Page only on symptoms users feel, such as error rate and latency against SLOs, and send cause-based signals to dashboards or tickets. Confidence: 0.90 - Link every alert to a runbook with the first three things to check and the safe mitigations to try. Confidence: 0.85 - Post status page updates at a fixed rhythm, such as every 30 minutes, even when the update is "still investigating". Confidence: 0.80 - Write customer updates in plain language about impact and next update time, without guesses about the cause. Confidence: 0.85 - Freeze unrelated deploys to the affected system while an incident is open. Confidence: 0.80 - Hand off explicitly when an incident outlasts a shift, with a written summary of state, open threads and next steps. Confidence: 0.85 - Hold a blameless postmortem for every SEV1 and SEV2 within five working days, focused on systems and decisions, not people. Confidence: 0.95 - Write postmortems with impact, timeline, contributing factors, what went well and owned action items with due dates. Confidence: 0.85 - Track postmortem action items in the normal backlog and review overdue ones every week, or they never get done. Confidence: 0.85 - Keep on-call rotations at least six people deep, with a secondary on call, and compensate people for the load. Confidence: 0.80 - Measure alert noise and delete or fix any alert that paged without needing action more than twice. Confidence: 0.85 - Run game days or chaos drills each quarter to practice the response process on purpose, not only during real outages. Confidence: 0.70 - Track time to detect, time to mitigate and incident count by severity, and avoid using them as individual performance targets. Confidence: 0.75
© f · CC0-1.0 · f/prompts.chat