# Hand Off Work to a Fresh Claude Agent

Long conversations make it hard to continue complex work across sessions. This skill creates a focused handoff summary and starts a background Claude agent with useful context.

## Install

```bash
npx skillstore add mattpocock/claude-handoff
```

## Metadata

- Status: approved
- Slug: mattpocock-claude-handoff
- Skillstore revision: r1
- Version status: missing
- Tree hash: 63c75926453f3535e569c1c6bc3f3d98edff15fa40c6debba7d235f75a8e4406
- Author: mattpocock
- GitHub username: mattpocock
- License: MIT
- Repository: https://github.com/mattpocock/skills/tree/main/skills/in-progress/claude-handoff/
- Ref: 3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 77
- Quality tier: bronze
- Public page: https://skillstore.pages.dev/skills/mattpocock-claude-handoff
- Manifest: https://skillstore.pages.dev/api/skills/mattpocock-claude-handoff/manifest

## Capabilities

- Summarizes the current conversation for continuation by another agent.
- Starts a background Claude agent with a descriptive session name.
- Includes suggested skills that the next agent should consider.
- References existing artifacts instead of repeating their full contents.
- Redacts sensitive information before using the summary as a prompt.

## Use Cases

- Continue Long Debugging Sessions: Create a concise handoff so a new agent can continue investigation without rereading the full conversation.
- Delegate Follow-Up Implementation: Start a background agent with context, open tasks, referenced artifacts, and suggested skills for the next phase.
- Preserve Context Before Switching Tasks: Capture current decisions and next steps before moving attention to another issue or support request.

## Prompt Templates

### Basic Handoff

```
Use claude-handoff to summarize this conversation and continue the same work in a fresh background agent.
```

### Focused Next Session

```
Use claude-handoff for a next session focused on finishing tests and preparing a concise status update.
```

### Artifact-Aware Handoff

```
Use claude-handoff and reference existing plans, diffs, and issue links instead of repeating their full contents.
```

### Review-Oriented Continuation

```
Use claude-handoff for a new agent that should review the implementation, cite existing artifacts, suggest skills, and protect sensitive data.
```

## Limitations

- It depends on the Claude CLI being available in the current environment.
- It does not validate whether referenced paths or URLs still exist.
- It cannot guarantee that all sensitive information is detected.
- It focuses on handoff context, not completing the original task itself.

## Best Practices

- Provide a clear focus area when starting the handoff.
- Keep important plans, diffs, and decisions in referenced artifacts.
- Review the handoff for sensitive information before sending it.

## Anti Patterns

- Use the skill when the current agent can finish a small task directly.
- Include secrets or personal data that the next agent does not need.
- Ask the next agent to ignore existing plans or artifacts without reason.

## Security Audit

- Audited at: 2026-07-09T09:31:57.087\+00:00
- Summary: The two static findings are false positives caused by Markdown inline command examples in SKILL.md. The skill is prompt-only and asks the agent to launch the Claude CLI background agent; no executable Ruby or shell script is present. No prompt injection, exfiltration, or malicious intent was found in the reviewed file.

## Stats

- Views: 0
- Downloads: 10
- Favorites: 0
- Popularity score: 0