claude-handoff

Launches a background Claude agent seeded with a conversation handoff summary.

Updated May 9, 2024
One-click install
npx skills add https://github.com/AceCodePt/dotfiles --skill claude-handoff-acecodept
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-handoff
Source: https://github.com/AceCodePt/dotfiles/tree/main/.config/opencode/flows/claude-handoff
Command: npx skills add https://github.com/AceCodePt/dotfiles --skill claude-handoff-acecodept

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Ending a long coding session often means losing context, forcing the next session to start from scratch. This Skill captures the current conversation state and immediately spins up a fresh background agent that continues the work without manual copy-pasting. ## Core Features & Use Cases - Automatic Handoff Summary: Writes a concise summary of the current conversation, referencing existing artifacts (specs, plans, commits) by path instead of duplicating them. - Background Agent Launch: Runs claude --bg --name "<descriptive name>" with the summary as the prompt, so the new agent starts in the current working directory and returns immediately. - Privacy-Aware Summaries: Redacts API keys, passwords, and personally identifiable information before the summary becomes the agent's prompt. - Use Case: You finish debugging half of a login issue at the end of the day. Invoke the handoff, and a named background agent picks up the remaining work with full context and suggested skills. ## Quick Start Ask the assistant to hand off the current conversation to a background agent focused on finishing the login bug fix.

Frequently Asked Questions about claude-handoff

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

FAQPage Schema
How do I continue a Claude session in a new agent?▼

Invoke the handoff flow, which writes a summary of the current conversation and launches a background agent via claude --bg with that summary as its prompt. The new agent starts in the current working directory and picks up the work immediately.

How do I name a background Claude agent?▼

Pass the -n or --name flag with a descriptive name, such as --name "Fix login bug". The name appears in the job list, session picker, and terminal title, making the agent easy to identify later.

Does the handoff summary include sensitive information?▼

No. The instructions require redacting API keys, passwords, and personally identifiable information before the summary is used as the agent's prompt, since the summary becomes part of the new agent's context.

What should the handoff summary contain?▼

It should capture the conversation state, reference existing artifacts like specs, plans, ADRs, and commits by path or URL instead of duplicating them, and include a suggested skills section for the next agent.

Can I manage the background agent after it launches?▼

Yes. The background agent returns immediately after launch and can be managed with the claude agents command, which lists and controls running background jobs.