community-automations/incident-responder

DevOps & Code

PublicClaude subagent

Incident Responder

The first ten minutes of an incident get lost to logistics: who is on, where do we talk, what do we tell customers. This responder handles that the moment severity crosses the line.

sonnet1 weekPagerDutySlackStatuspageDatadog
ClaudeClaude
ROI for
README.md

Why this subagent

The first ten minutes of an incident get lost to logistics: who is on, where do we talk, what do we tell customers. This responder handles that the moment severity crosses the line.

It opens a war-room channel, pulls in the on-call and service owners, and drafts the first internal and external updates from the alert. As the incident moves it tracks the timeline, so when it is over the postmortem half-writes itself instead of being reconstructed from memory.

How it runs

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

Sample output

json
// Sample output
// (generated when the pipeline finishes)

Given an incident-level alert, return a JSON response opening a war-room channel, the assigned responders, and drafted internal and external status updates.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.