Getting paged at 2am means hunting for the runbook, the last deploy, and the right dashboard while the clock runs. This helper gathers all of it the moment the page fires.
sonnet4 daysPagerDutySlackDatadogGitHub
Claude
84ROI
73Scale
$2.4k95Saved
ROI for
README.md
Why this subagent
Getting paged at 2am means hunting for the runbook, the last deploy, and the right dashboard while the clock runs. This helper gathers all of it the moment the page fires.
It reads the alert, pulls the matching runbook and the recent deploys to that service, and surfaces the dashboards and similar past incidents. Everything lands in one Slack thread, so the on-call engineer starts diagnosing instead of searching, and shaves real minutes off the response.
How it runs
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.
Pull the matching runbook and the recent deploys that touched that service.
pending
Surface relevant dashboards and the last few similar incidents for context.
pending
Post a single threaded message with the runbook link, recent changes, and next steps.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given a PagerDuty alert, return a JSON brief with the matching runbook, recent deploys to the affected service, relevant dashboards, and suggested first steps.
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.