All loops
OpsHard 7 min· claude-sonnet-4-5

Incident commander

Drives postmortems from PagerDuty + Slack history.

NOT DEPLOYEDNOT DEPLOYED
0169ms
Trigger
cron(0 7 * * *) fired · every day · 07:00
021249ms
Agent
claude-sonnet-4-5 · in 1749 tok · out 736 tok
03239ms
Tools
fetch-mcp/anthropic:messages.create → 200 OK · 129ms
0459ms
Verify
schema check · zod v3 passed
05149ms
Output
pagerduty ack · incident summary posted
0629ms
Notify
audit log written · runbook link attached
SUCCESS
0%
0 runs
P50
0ms
median
P95
0ms
tail
AVG COST
per run
LAST OK
never
LAST FAIL
never
none
Latency · last 30 runs0 samples
no runs yet
Latest output · what your users see
Grafana OnCallwarning

p95 latency on /api/checkout crossed 1200ms for 6 min. Correlated deploy: web@d41f2a. Suggested rollback command attached.

deduped ×7·runbook: runbooks/checkout-latency.md#rollback
// press Test to run once · Watch live to keep streaming · Deploy to make it real
The problem

Ops work is repetitive, urgent, and easy to drop. Humans pay the tax.

The outcome

A scheduled agent that does the chore, posts the result, and escalates only when needed.

Ingredients & skills

Secrets
  • ANTHROPIC_API_KEY
Providers
  • Anthropic
MCP servers
  • fetch-mcp
#ops#sre#pagerduty

How it works

Drives postmortems from PagerDuty + Slack history.

Step 1

1 — Fetch

Read the relevant telemetry. Scope keys to read-only.

Step 2

2 — Analyse

Claude summarises + ranks. Empty input ⇒ no message (no noise).

Step 3

3 — Post

Slack, email, or PagerDuty depending on severity.

One-line deploy

The button above runs the same command with your saved config. This is the raw CLI form.

bash
npx claudeloops deploy incident-commander

Related loops