claude-handoff

Use it when: the current conversation should continue in a fresh agent, starting right away
It does: summarizes the conversation, then starts a background Claude Code agent with that summary as its prompt
You get: a new, named agent already working in the same folder, which you manage with claude agents
Unlike handoff: that skill, by the same author, only writes the summary for you to pass on; this one also launches the next agent
Needs: Claude Code, whose claude --bg command starts background agents
Runs: only when you invoke it; it sits in its author's in-progress folder, so expect changes

TLDR

The agent writes a summary of the conversation to your system's temp folder, then runs claude --bg with a descriptive name and that summary as the prompt. The new agent starts in the current folder and the command returns at once, so your session carries on while the new one works. The summary names the skills the next agent should load, points to specs, plans, issues, commits and diffs by path or URL instead of copying them, and removes API keys, passwords and personal details, since it becomes the new agent's prompt. Say what the next session is for, and it tailors the summary to that.

Summarizes the skill at 5beb35b.

npx skills add https://github.com/mattpocock/skills --skill claude-handoff

skills.sh page · Source on GitHub · All skills from mattpocock/skills

Installs: 298,145 on skills.sh, Sep 21, 2026
Repo stars: 266,454 mattpocock/skills
First seen: Jul 2, 2026 on skills.sh

Weekly installs

27.2K

+32% over 8 weeks · week to Sep 21

Weekly values

Week to	Installs
Aug 3	20,517
Aug 10	23,625
Aug 17	20,366
Aug 24	29,918
Aug 31	32,460
Sep 7	32,375
Sep 14	29,286
Sep 21	27,180

Category	category:planning category:software-engineering Make the agent question you and write the plan down before it writes code. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type	type:command A one-shot action you invoke by name, such as turning the conversation into a PRD.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:claude-code Uses Claude Code features such as hooks or background agents.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	handoff multi-agent

SKILL.md

From mattpocock/skills at 5beb35b. Checked daily, last changed Oct 20, 2026.

Frontmatter

name: claude-handoff
description: Hand the current conversation off to a fresh background agent that picks up the work immediately.
argument-hint: "What will the next session be used for?"
disable-model-invocation: true

Write a handoff summary of the current conversation so a fresh agent can continue the work. Save it to the temporary directory of the user's OS, then launch a background agent seeded with it as its prompt: claude --bg --name "<descriptive name>" -- "$(cat <summary file>)". Passing the file keeps the shell from running backticks or expanding $ in the summary. It starts in the current working directory and returns immediately; the user manages it with claude agents.

Always pass -n/--name with a descriptive name (e.g. --name "Fix login bug"); it sets the display name shown in the job list, session picker, and terminal title.

Include a "suggested skills" section in the summary, naming which skills the next agent should call the Skill tool for.

Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.

Redact any sensitive information, such as API keys, passwords, or personally identifiable information, since the summary becomes the agent's prompt.

If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.