About claude-handoff
claude-handoff is a skill for handing ongoing work from a conversation to a fresh agent. It creates a background agent in the current working directory with a concise, privacy-conscious summary and suggested skills.
Key features
- 01Launch a background agent
- 02Summarize conversation context
- 03Include suggested skills
- 04Redact sensitive information
- 05Avoid duplicating project artifacts
Use cases
- 01Continue a task in a fresh agent session
- 02Pass focused next-session instructions
- 03Preserve context while referencing existing plans
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/claude-handoffin Claude Code to confirm it loaded.
Bundled filesagents/openai.yaml
Details
From the project READMEWrite a handoff summary of the current conversation so a fresh agent can continue the work. Instead of saving it, launch a background agent seeded with the summary as its prompt: claude --bg --name "<descriptive name>" "<handoff 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, which suggests skills that the agent should invoke.
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 — 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.