claude-handoff

Launches a background agent seeded with a handoff summary of the current conversation.

2|Updated Jun 21, 2026
One-click install
npx skills add https://github.com/IsKenKenYa/skills --skill claude-handoff-iskenkenya
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-handoff
Source: https://github.com/IsKenKenYa/skills/tree/main/skills/in-progress/claude-handoff
Command: npx skills add https://github.com/IsKenKenYa/skills --skill claude-handoff-iskenkenya

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When a conversation grows long or a task needs to continue in a fresh session, context is lost. This Skill writes a concise handoff summary of the current conversation and immediately launches a new background agent seeded with that summary, so work continues without manual copy-pasting. ## Core Features & Use Cases - Automatic Handoff Summary: Distills the current conversation into a prompt for a fresh agent, referencing existing artifacts (specs, plans, ADRs, commits) by path instead of duplicating them. - Background Agent Launch: Runs claude --bg --name "<descriptive name>" in the current working directory, returning immediately while the user manages jobs via claude agents. - Privacy-Aware Summaries: Redacts sensitive information such as API keys, passwords, and personally identifiable information before the summary becomes the new agent's prompt. - Use Case: You have been debugging a login issue in a long session and want a fresh agent to continue. Invoke the skill with a note like "continue fixing the login bug", and a named background agent picks up the work with a suggested-skills list. ## Quick Start Ask the assistant to hand off the current conversation to a new background agent named for your next task, optionally describing what the next session should focus on.

Frequently Asked Questions about claude-handoff

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I hand off a Claude conversation to a new agent?

Invoke the skill, optionally describing what the next session should focus on. It writes a handoff summary of the current conversation and launches a background agent with `claude --bg --name "<name>"` seeded with that summary.

How do I run a Claude agent in the background?

Use `claude --bg --name "<descriptive name>" "<prompt>"`, which starts the agent in the current working directory and returns immediately. You manage running background agents with the `claude agents` command.

Does the handoff summary include sensitive information?

No. The skill explicitly redacts sensitive information such as API keys, passwords, and personally identifiable information, because the summary becomes the new agent's prompt.

What happens to specs and plans already written during the session?

They are not duplicated in the summary. The skill references existing artifacts such as specs, plans, ADRs, issues, commits, and diffs by path or URL so the next agent can read them directly.

Can I control what the next session focuses on?

Yes. Any arguments you pass are treated as a description of the next session's focus, and the handoff summary is tailored accordingly, including a suggested-skills section for the next agent.