Oncall Irm

What it does

When your agent uses it

• Wiring Alertmanager to OnCall
• Deciding which team gets paged
• Building rotations from a Google Calendar / iCal
• Hooking up Slack notifications

Example prompts

• “page the platform team on critical alerts”
• “send Prometheus alerts to Slack”
• “set up our on-call rota”
• “/oncall-irm”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1Wire Alertmanager → IRM and verify routing
2. 2Build an escalation chain + verify
3. 3Create a schedule from iCal + verify "who is on-call right now"

What it can do on your machine

Read from SKILL.md and the folder at commit 1ccacf2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl
  • jq

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • grafana.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Oncall Irm loads about 1.4k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 239 tokens; SKILL.md has 218 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~239

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from grafana/skills at commit 1ccacf2, republished under its Apache-2.0 licence (© grafana). 218 words, ~1,380 tokens.

name

oncall-irm

description

Route alerts, run on-call rotations, and drive incidents in Grafana IRM / OnCall — integrations (Alertmanager / Grafana Alerting / generic webhook / PagerDuty), Jinja2 routing + grouping templates, escalation chains (wait → notify schedule → notify team → webhook → auto-resolve), schedules (web + iCal + Terraform `grafana_oncall_schedule`), Slack chatops with Acknowledge/Resolve/Silence, and the P1-P4 incident lifecycle. Use when wiring Alertmanager to OnCall, deciding which team gets paged, building rotations from a Google Calendar / iCal, hooking up Slack notifications, or declaring an incident from an alert — even when the user says "page the platform team on critical alerts", "send Prometheus alerts to Slack", "set up our on-call rota", "escalation policy", or "auto-resolve when the alert clears" without naming OnCall / IRM. Heads up — OnCall OSS is in maintenance mode (archived March 2026); Grafana Cloud users should use IRM.

license

Apache-2.0

# 1. In IRM: New integration → Alertmanager. Copy the webhook URL.
# 2. alertmanager.yml (see references/integrations.md for full block):
receivers:
  - name: grafana-oncall
    webhook_configs:
      - url: https://<stack>.grafana.net/integrations/v1/alertmanager/<id>/
        send_resolved: true
        max_alerts: 100

# 3. Test the routing template BEFORE going live (UI: Integration → Route → "Preview")
#    Paste a sample payload (use a real Alertmanager test webhook). Expect:
#      Routing result: True
#      Escalation chain selected: <expected chain>
#    If False — your Jinja expression is wrong; fix and re-preview.

# 4. End-to-end test — fire amtool (or any test webhook) at the URL
amtool alert add foo severity=critical team=platform --alertmanager.url http://localhost:9093

# 5. Verify in IRM → Alert Groups (should appear within ~5s) — confirm:
#    - Correct route fired
#    - Correct schedule/user notified
#    - Slack message appeared in the configured channel

1. Notify "Primary On-Call" (Important Notifications)
2. Wait 5 min
3. Notify "Primary On-Call" (Default Notifications)
4. Wait 10 min
5. Notify team "Platform"
6. Trigger outgoing webhook (PagerDuty / ticket)

# Verify: create a test alert (UI → Integration → "Send demo alert"),
# then watch the alert-group timeline tick through steps 1 → 6.
# Use IRM → Escalation Chains → "Test" if available, otherwise the demo alert is the canonical check.

# 1. Create the schedule
curl -X POST https://<stack>.grafana.net/api/v1/schedules/ \
  -H "Authorization: <token>" -H "Content-Type: application/json" \
  -d '{"name":"Platform On-Call",
       "ical_url_primary":"https://calendar.example.com/platform.ics",
       "slack":{"channel_id":"C123456ABC","user_group_id":"S123456ABC"}}'

# 2. Verify the schedule was created
curl -s https://<stack>.grafana.net/api/v1/schedules/ \
  -H "Authorization: <token>" | jq '.results[] | select(.name=="Platform On-Call")'

# 3. Verify who is on-call right now
curl -s https://<stack>.grafana.net/api/v1/schedules/<schedule_id>/next_shifts/ \
  -H "Authorization: <token>" | jq '.results[0]'
# Expect a shift starting now (or recently) with the right user_id.

© grafana, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/grafana-cloud/oncall-irm of grafana/skills.

• SKILL.md
• references/integrations.md
• references/templates-schedules.md

Open the folder on GitHubat commit 1ccacf2