mcpField
C
claude-handoff

claude-handoff

github.com/mattpocockAgent workflows305.7k434.7k installsUpdated 1d ago
Repository

About claude-handoff

claude-handoff is a skill that packages a conversation summary for a fresh agent and starts that agent in the background. It saves the prompt to a temporary file, includes suggested skills, and avoids repeating details already captured in project artifacts.

Key features

  1. 01Summarize the current conversation for continuation
  2. 02Save the summary in the OS temporary directory
  3. 03Launch a named background agent
  4. 04Suggest skills for the next agent
  5. 05Redact sensitive information and reference existing artifacts

Use cases

  1. 01Hand off ongoing work to a fresh agent
  2. 02Start a background session focused on supplied arguments
  3. 03Pass project context without duplicating existing documentation

Install

Copy the command and run it in a terminal.

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

After installing, type/claude-handoffin Claude Code to confirm it loaded.

Bundled filesagents/openai.yaml

Details

From the project README

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.

Comments

Markdown supported