All loops
OpsEasy 8 min· claude-opus-4-1

On-call digest

Summarises overnight pages every morning.

Read the full Ops build guide →
NOT DEPLOYEDNOT DEPLOYED
0168ms
Trigger
cron(0 7 * * *) fired · every day · 07:00
021248ms
Agent
claude-opus-4-1 · in 1748 tok · out 736 tok
03238ms
Tools
fetch-mcp/anthropic:messages.create → 200 OK · 128ms
0458ms
Verify
schema check · json-schema draft-2020 passed
05148ms
Output
slack #ops · alert deduped x4
0628ms
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
Datadogwarning

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

deduped ×6·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

Summarises overnight pages every morning.

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 on-call-digest

Related loops