Handoff

Generates a clipboard-ready prompt you can paste into a fresh Claude session when you want another agent to pick up a task. Strips out filesystem paths and replaces them with portable anchors like repo URLs, branch names, issue links, and exact error text so the handoff works regardless of where the receiving agent starts. The prompts explicitly ask the new agent to review independently first, decide if the task is still valid, and report findings before making changes. Useful when you're handing off mid-investigation, delegating a bug fix, or want a second agent to validate an approach without inheriting your assumptions. Keeps you from accidentally leaking workspace-specific details or writing command-only work orders that skip the thinking step.

skills.sh installs: 700
GitHub stars: 1.1K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add openclaw/agent-skills --skill handoff --agent claude-code

Installs into .claude/skills of the current project.

Files

Handoff

Write a clipboard-ready prompt for another agent to investigate, discuss, or work on a specific task.

Use when the user asks for handoff <task>, "write a handoff", "delegate this", or wants a prompt for another agent.

Workflow

Identify the task from the user text. If the user gives only a short label, infer from the current repo, recent discussion, branch name, linked issue/PR, docs, and obvious nearby context.
Gather enough context to write a useful handoff: repo/product identity, relevant issue/PR/branch names, likely modules, constraints, and known symptoms. Do not perform the receiving agent's full independent review or decide the final technical direction for them.
Write a standalone prompt preserving the requested mode, existing authority, accepted decisions, completed proof, remaining work, and completion condition.
Copy the full prompt to the clipboard.
Final reply: terse confirmation with the task title. Do not paste the full prompt unless the user asks.