Official agent skill

Handoff

by anthropics in anthropics/oncall-kit

Write the weekly on-call handoff: everything the incoming on-call needs, triage-ready, posted to the channel at shift boundary.

OfficialApache-2.0Auto-check passedDevOps & Cloud

Install Handoff

skills CLI
$ npx skills add anthropics/oncall-kit --skill handoff -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/oncall-kit handoff --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/oncall-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/handoff .claude/skills/handoff && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
handoff
GitHub stars
210
Token cost
~1.2k tokens
SKILL.md length
639 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

Write the weekly on-call handoff: everything the incoming on-call needs, triage-ready, posted to the channel at shift boundary.

  • The weekly routine fires
  • SKILL.md covers Sources — sweep all of them, Format, Drift check (required section) and Discipline
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Someone asks for a handoff / shift summary / catch the next on-call up

What it does

Handoff is an agent skill from anthropics/oncall-kit, published by the product's own GitHub organization. Write the weekly on-call handoff: everything the incoming on-call needs, triage-ready, posted to the channel at shift boundary. Use when the weekly routine fires, or when someone asks for a handoff / shift summary / "catch the next on-call up".

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Incident response. The repository describes itself as: Starter kit for a Claude-assisted on-call: mines your incident history into triage playbooks, sets up through human-approved gates, and runs read-only in your Slack channel —… The licence is Apache-2.0.

When your agent uses it

  • The weekly routine fires
  • Someone asks for a handoff / shift summary / catch the next on-call up

Example prompts

  • “catch the next on-call up”
  • “/handoff”

What it can do on your machine

Read from SKILL.md and the folder at commit c03282c. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Handoff loads about 1.2k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 639 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 anthropics/oncall-kit at commit c03282c, republished under its Apache-2.0 licence (© anthropics). 639 words, ~1,164 tokens.

Download SKILL.mdSave it as .claude/skills/handoff/SKILL.md (or your agent's skills folder).
name
handoff
description
Write the weekly on-call handoff: everything the incoming on-call needs, triage-ready, posted to the channel at shift boundary. Use when the weekly routine fires, or when someone asks for a handoff / shift summary / "catch the next on-call up".
<!-- Copyright 2026 Anthropic PBC -->
<!-- SPDX-License-Identifier: Apache-2.0 -->

Handoff

Standing rules in CLAUDE.md apply — especially rules 10 and 11: fresh reader, lead with what to do. The incoming on-call missed everything; this document is their entire week's context, and it must arrive as work they can start, not "here's what happened".

Sources — sweep all of them

Fan out across every capability in STACK.md for the shift window (default: the week since the last handoff):

  • pager — every page and incident: state, severity, resolution
  • alert-channels — what fired, what people said, what never got a thread
  • code — merges/PRs touching on-call-relevant paths; reverts; deploys
  • metrics — week-over-week trend of the health signals in ONCALL.md
  • lessons.md — every entry appended this shift
  • each incident record's history over the shift window

Cross-reference: an alert with no thread, a lessons entry with no incident, a metric trending wrong with no alert — these orphans are usually the "watch this week" items.

Format

Post to the channel as a message with the exec summary, full doc attached or linked:

📋 On-call handoff — week of {{date}}

Exec summary: N incidents (n resolved, n monitoring). N pages. Anything systemic in one clause. On-call health: the required weekly metric — incidents and pages vs. last week, split by business-hours / off-hours, false pages, the rubber-stamp fraction (diagnoses acted on with no recorded verification step — the early warning that humans stopped cross-examining; see eval/replay.md), and whether the trend is up or down. This section is how the whole setup is measured over time (see eval/replay.md), so never omit it and never soften it. Intake health: median and worst time from symptom onset to incident declared this week (onset from the alert/thread timeline; declaration from the incident record). If incidents routinely run 40 minutes before anyone declares one, that's the process finding of the week — you can't fix an intake path you don't measure. Watch this week: the 1–3 things most likely to page you, each with why and a link to its pattern (lessons.md tag or reference file). Start here: the single highest-priority open item, with its current state and next action. Full doc: [link] · New to this channel? Read ONBOARD.md — how to read a diagnosis, challenge one, or silence a routine.

The full doc, per incident: what happened (one fresh-reader sentence, links) · what it means (pattern or one-off? systemic risk?) · what you should do (nothing / monitor / action, with the action named).

Then: open items ranked by "will this page you?", not by age. Preventable repeats called out as playbook gaps with proposed reference-file amendments (rule 9 — fix the playbook, not just the incident).

Show full SKILL.md (221 more words)Show less

Drift check (required section)

The ground moves between incidents; this is where the kit notices. Each week, flag:

  • any STACK.md binding that failed or 403'd during the week's work
  • any reference file whose first-checks cite a tool or query that no longer responds
  • anything in the deploys feed or announcement channels suggesting the infrastructure changed under the playbooks — a migration completed, a tool replaced, a service renamed
  • the routine registry vs. reality: does the "Standing work" canvas match the channel's actual routines? Fix the registry; flag any routine that exists but was never registered
  • open incidents with no update in >{{72h}} — the zombie list, each with its three-leg staleness evidence per ONCALL.md's lifecycle section, framed as "close it or update it", never closed by Claude (rule 2)

Each flag arrives as a proposal, never an edit (rule 9): "re-run Discover for this binding," a reference-file amendment PR, or "re-run the replay against post-change incidents" (see eval/replay.md's re-validation triggers). A quiet week with no drift gets one line: "no drift detected."

Discipline

  • "Here's what happened" without "start here" is a diary, not a handoff — the priorities are the point.
  • Never soften a preventable repeat. Write it plainly: "2 auto-reverts, both preventable."
  • If the week was quiet, say so in two lines and stop. Padding a quiet week erodes trust in loud ones.

© anthropics, 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

Just SKILL.md in skills/handoff of anthropics/oncall-kit.

Open the folder on GitHubat commit c03282c

Compare with similar skills

Handoff next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Handoff this skillanthropics/oncall-kit210—~1.2kAutomated safety check: PassApache-2.0
Kubernetes Network Root Cause Analysiskubeshark/kubeshark12k—~5.3kAutomated safety check: PassApache-2.0
UModel Root Cause Analysisalibaba/UnifiedModel412—~1.9kAutomated safety check: PassCustom licence
Learningskortix-ai/suna20k—~1.1kAutomated safety check: PassCustom licence
Oncallpigweed-project/pigweed548—~992Automated safety check: PassApache-2.0
Loop Triage Reportcobusgreyling/loop-engineering11k—~500Automated safety check: PassMIT

Similar skills

  • Investigates past Kubernetes incidents from Kubeshark traffic snapshots: takes captures, dissects API calls, extracts PCAPs and compares traffic over time.

    12k GitHub stars~5.3k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • UModel Root Cause Analysis

    alibaba/UnifiedModel

    Investigates a service incident to its root cause by querying a UModel object graph alongside metrics, logs, topology and recent deployments.

    412 GitHub stars~1.9k tokensUpdated 14 days ago
    DevOps & CloudAuto-check passed
  • Learnings

    kortix-ai/suna

    The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident.

    20k GitHub stars~1.1k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Oncall

    pigweed-project/pigweed

    Pigweed oncall rotation runbooks and maintenance workflows (such as rolling CIPD client tools for b/315378787).

    548 GitHub stars~992 tokensUpdated today
    DevOps & CloudAuto-check passed
  • Loop Triage Report

    cobusgreyling/loop-engineering

    Turns CI failures, open issues, recent commits and chat threads into a prioritized markdown report that an automation loop can act on without inventing architecture work.

    11k GitHub stars~500 tokensUpdated today
    DevOps & CloudAuto-check passed
  • Axiom SRE Investigator

    openclaw/clawhub

    Investigates incidents and production problems with hypothesis-driven debugging, queries Axiom observability data when available, and keeps secrets out of commands and output.

    9.5k GitHub stars~7.1k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from anthropics/oncall-kit

  • Weather

    anthropics/oncall-kit

    Official

    The optional standing status report ("the weather"): compile open incidents, build health, merge-queue stats, and deploy lag into one always-current report page, and post to the channel only when a…

    210 GitHub stars~3.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Oncall Setup

    anthropics/oncall-kit

    Official

    Bootstrap a Claude-assisted on-call for this channel/repo: discover the available connectors, mine incident history into draft triage playbooks, interview the human for policy, validate against…

    210 GitHub stars~4.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Triage

    anthropics/oncall-kit

    Official

    Investigate an alert or incident in this channel: classify the symptom, load the matching triage reference, check lessons.md for known causes, and post a grounded first-pass diagnosis with evidence…

    210 GitHub stars~2.1k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Handoff

What does Handoff do?

Write the weekly on-call handoff: everything the incoming on-call needs, triage-ready, posted to the channel at shift boundary. Handoff is an agent skill from anthropics/oncall-kit, published by the product's own GitHub organization. Write the weekly on-call handoff: everything the incoming on-call needs, triage-ready, posted to the channel at shift boundary.

When should I use Handoff?

Handoff fits situations like: the weekly routine fires; someone asks for a handoff / shift summary / catch the next on-call up.

How do I install Handoff in Claude Code?

Run `npx skills add anthropics/oncall-kit --skill handoff -a claude-code`. Or copy the skill folder (skills/handoff in anthropics/oncall-kit) into .claude/skills/handoff in your project. Claude Code loads it when a task matches its description.

How do I install Handoff in Codex?

Run `npx skills add anthropics/oncall-kit --skill handoff -a codex`. Or copy the skill folder (skills/handoff in anthropics/oncall-kit) into .agents/skills/handoff in your project. Codex loads it when a task matches its description.

Can I use Handoff in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/oncall-kit --skill handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/handoff, .gemini/skills/handoff, .github/skills/handoff and .opencode/skills/handoff in your project.

What does Handoff need to run?

SKILL.md names no scripts, command-line tools or credentials: Handoff is instructions for the agent only.

Does Handoff access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Handoff safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Handoff use?

Handoff is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Handoff use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Handoff?

Skills that share tags, products or a category with Handoff: Kubernetes Network Root Cause Analysis (kubeshark/kubeshark, 12k stars), UModel Root Cause Analysis (alibaba/UnifiedModel, 412 stars), Learnings (kortix-ai/suna, 20k stars) and Oncall (pigweed-project/pigweed, 548 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Handoff?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/oncall-kit, which has 210 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 6, 2026.

Source: anthropics/oncall-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.