on-call-handoff

on-call-handoff is a command for Claude Code from latestaiagents/agent-skills. It costs 16 tokens per session (961 once invoked), scanned A, original, MIT.

A report template for handing an on-call shift to another engineer. On-call means being responsible for responding to service problems during a scheduled period.

In plain words
What is it for?
Use it to record open incidents, deployments in progress, unusual error rates, next steps, rollback instructions, and other watch items.
Why use it?
It preserves active incident details, current context, contacts, and items to watch so the incoming engineer can continue safely.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the devops-sre plugin — 8 skills, 6 commands shipped together

Good fit Use it to record open incidents, deployments in progress, unusual error rates, next steps, rollback instructions, and other watch items.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/latestaiagents/agent-skills/on-call-handoff
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install devops-sre, the plugin that ships this one along with the rest of its 8 skills, 6 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for on-call-handoff

README.md
[![agentmods](https://agentmods.dev/badge/commands/latestaiagents/agent-skills/on-call-handoff/github.svg)](https://agentmods.dev/commands/latestaiagents/agent-skills/on-call-handoff)
Your own site
<a href="https://agentmods.dev/commands/latestaiagents/agent-skills/on-call-handoff"><img src="https://agentmods.dev/badge/commands/latestaiagents/agent-skills/on-call-handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for on-call-handoff

Your own site · 80×15
<a href="https://agentmods.dev/commands/latestaiagents/agent-skills/on-call-handoff"><img src="https://agentmods.dev/badge/commands/latestaiagents/agent-skills/on-call-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 961 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00961
Opus 5 $0.00008 $0.00481
Sonnet 5 $0.00003 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 10d ago against content hash f6dbb6c6f456, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

on-call-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/devops-sre/commands/on-call-handoff.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/on-call-handoff

Generate a comprehensive handoff report for on-call rotation transitions.

What I Need

Tell me:

  • Your name (outgoing on-call)
  • Incoming on-call engineer's name
  • Any specific issues to highlight

Or just run /on-call-handoff and I'll gather from connected tools.

Generated Handoff Report

# On-Call Handoff Report

**From:** [Outgoing Engineer]
**To:** [Incoming Engineer]
**Rotation:** [Team Name]
**Handoff Time:** YYYY-MM-DD HH:MM UTC

---

## 🚨 Active Incidents

| ID | Severity | Status | Summary | Started |
|----|----------|--------|---------|---------|
| INC-123 | SEV2 | Investigating | API latency spike | 2h ago |

**INC-123 Context:**
- Root cause: Suspected database connection pool exhaustion
- Current state: Scaled up read replicas, monitoring
- Next steps: Review connection pooling config tomorrow
- Key contacts: @dba-team if it recurs

---

## ⚠️ Watch Items

### High Priority
1. **Deployment in progress** - v2.3.4 rolling out to prod-west
   - Canary at 10%, promoting to 50% at 14:00 UTC
   - Rollback command ready: `kubectl rollout undo deploy/api`

2. **Elevated error rate** - payments-service at 0.5% (normal: 0.1%)
   - Started after morning deploy, monitoring
   - No user complaints yet

### Medium Priority
3. **Planned maintenance** - RDS maintenance window tonight 02:00-04:00 UTC
   - Expected: 30s failover, auto-reconnect should handle
   - Runbook: `database/rds-maintenance-checklist`

---

## 📊 System Health Summary

| Service | Status | Notes |
|---------|--------|-------|
| api-gateway | 🟢 Healthy | |
| user-service | 🟢 Healthy | |
| payments | 🟡 Degraded | Elevated errors, monitoring |
| search | 🟢 Healthy | |
| notifications | 🟢 Healthy | |

**Key Metrics (Last 24h):**
- Error rate: 0.12% (SLO: <0.5%) ✓
- P99 latency: 245ms (SLO: <500ms) ✓
- Availability: 99.95% (SLO: 99.9%) ✓

---

## 📝 Shift Summary

### Incidents Handled
- INC-121 (SEV3) - Resolved - Cache invalidation issue
- INC-122 (SEV4) - Resolved - Flaky test in CI

### Changes Made
- Scaled worker pool 3→5 instances (can scale back Monday)
- Updated alerting threshold for memory usage (was too noisy)

### Deferred Work
- [ ] Investigate slow query on reports endpoint (non-urgent)
- [ ] Update runbook for certificate rotation

---

## 📞 Key Contacts

| Role | Name | Reach |
|------|------|-------|
| Secondary On-Call | @jane | Slack, PagerDuty |
| Engineering Manager | @bob | Slack (daytime only) |
| DBA On-Call | @dba-team | PagerDuty |
| Security | @security-team | PagerDuty (SEV1 only) |

---

## 🔗 Quick Links

- [Runbooks](https://wiki.company.com/runbooks)
- [Dashboards](https://datadog.com/dashboard/main)
- [Incident Slack](https://slack.com/channels/incidents)
- [PagerDuty Schedule](https://pagerduty.com/schedules)
- [Status Page Admin](https://statuspage.io/admin)

---

*Handoff generated at YYYY-MM-DD HH:MM UTC*
*Good luck! 🍀*

Read the full file on GitHub · 136 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 136 lines · 16 tokens per session scan A f6dbb6c6f456

Subscribe to this mod's changes

on-call-handoff is a command published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 961 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.