incident-response
Run an incident response workflow — triage, communicate, and write postmortem
by anthropicsFree
Description
incident-response is a command from Anthropic's knowledge-work plugins, listed on skills.sh. It manages an incident from detection through to the postmortem, covering triage, communication and the written review. It is triggered by phrases such as we have an incident or production is down, or by an alert that needs a response. The command has three modes. The new mode starts an incident from a description. The update mode posts a status update for the team. The postmortem mode generates a postmortem from the incident data. It is run with /incident-response followed by the mode and any details. A connectors guide explains which tools are connected. It suits engineering and operations teams that need a clear, disciplined way to run an incident and to write the review afterwards, with the communication kept consistent throughout.…
Highlights
- Triage, communication and postmortem
- New, update and postmortem modes
- Triggered by incident phrases or alerts
- Postmortem drawn from incident data
Ratings & Reviews
No ratings yet
Be the first to rate incident-response.
People also visit
intent-driven-development
Turn ambiguous or high-impact product and engineering changes into scoped
production-scheduling
Codified expertise for production scheduling, job sequencing, line balancing
unified-notifications-ops
Operate notifications as one ECC-native workflow across GitHub, Linear
incident-response FAQ
What does incident-response do?
It runs an incident from detection to a postmortem, covering triage, status communication and the written review.
How do I install it?
Run: npx skills add https://github.com/anthropics/knowledge-work-plugins --skill incident-response
What are the modes?
new to start an incident, update to post a status update, and postmortem to write the review.
What starts the workflow?
Phrases such as we have an incident or production is down, or an alert that needs a response.
Has it been checked for security?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Pass and Snyk Pass.
What are the best incident-response alternatives?
Popular alternatives to incident-response include intent-driven-development, latency-critical-systems and production-scheduling. See all incident-response alternatives