claude-handoff

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

2|Updated May 12, 2026
One-click install
npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill claude-handoff-tajo9128
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-handoff
Source: https://github.com/tajo9128/BioDockify-Pharma-AI/tree/main/.agents/skills/claude-handoff
Command: npx skills add https://github.com/tajo9128/BioDockify-Pharma-AI --skill claude-handoff-tajo9128

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long conversations lose context or hit limits, forcing users to manually re-explain work when starting a fresh session. This Skill writes a handoff summary of the current conversation and immediately launches a background agent seeded with that summary, so work continues without interruption. ## Core Features & Use Cases - Automatic Handoff Summary: Generates a concise summary of the current conversation, referencing existing artifacts (specs, plans, ADRs, commits) by path instead of duplicating them. - Background Agent Launch: Runs claude --bg --name "<descriptive name>" with the summary as the prompt, returning immediately while the agent works in the current directory. - Suggested Skills Section: Recommends which skills the next agent should invoke, and redacts sensitive data like API keys or PII from the summary. - Use Case: You have been debugging a login issue for hours and the context is nearly exhausted. Invoke the handoff to spin up a fresh background agent named "Fix login bug" that picks up exactly where you left off. ## Quick Start Ask the assistant to hand off the current conversation to a background agent focused on fixing the login bug.

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 conversation in a new session?

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

How do I run a background agent with the claude CLI?

Use the command claude --bg --name "<descriptive name>" "<prompt>" to start a background agent that returns immediately. Always pass a descriptive name so the job is identifiable in the job list, session picker, and terminal title.

How do I manage background agents after a handoff?

Manage running background agents with the claude agents command. The descriptive name passed via --name appears in the job list and session picker, making it easy to identify each handoff.

Does the handoff summary include sensitive information?

No, the skill explicitly redacts sensitive information such as API keys, passwords, and personally identifiable information before the summary becomes the agent's prompt. It also references existing artifacts by path instead of duplicating content.

When should I use a handoff instead of continuing the same session?

Use a handoff when the current conversation has grown long or context is nearly exhausted and a fresh agent would perform better. It is not needed for short tasks where the existing session still has sufficient context.