What makes Claude Handoff notable?

983 downloads. Trust evidence available

How should Claude Handoff be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Claude Handoff

Writes a structured handoff package when local agent determines cloud Claude Code is needed. This is the ONLY path from local pipeline to cloud — the agent n... Skill: Claude Handoff Owner: stephenlthorn Summary: Writes a structured handoff package when local agent determines cloud Claude Code is needed. This is the ONLY path from local pipeline to cloud — the agent n... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-21T13:46:35.122Z | auto claude-handoff 1.0.0 - Initial release of the Claude Handoff skill. - Generates a structured handoff package when local agent dete

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

983

Updated

Oct 11, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 983 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 983 downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed Apr 21, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.0release
claude-handoff 1.0.0 - Initial release of the Claude Handoff skill. - Generates a structured handoff package when local agent determines cloud Claude Code is needed. - Supports user review and manual approval before any Claude Code invocation; never auto-invokes Claude. - Triggers on hard gates (e.g. iOS .swift files), escalation score, build failure, low reflection confidence, or explicit user request. - Summarizes context, rationale, proposed plan, local attempts, and provides ready-to-run Claude commands. - Helps users control Claude Max quota usage with clear cost estimates.
Observed Apr 21, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s1781macwsy8b25gaqa558qrx5858x3k:claude-handoff

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-stephenlthorn-claude-handoff/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

19,997 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: claude-handoff
version: 1.0.0
description: |
  Writes a structured handoff package when local agent determines cloud
  Claude Code is needed. This is the ONLY path from local pipeline to cloud —
  the agent never auto-invokes Claude. The user reviews the handoff, decides
  whether to run Claude Code, and retains full control over Max quota spend.
triggers:
  - hard gate hit (iOS .swift file in scope)
  - soft gate exceeded (escalation score >= 8)
  - build feedback exhausted (3 failed iterations)
  - reflection confidence LOW after max passes
  - explicit user request: "hand this to Claude"
tools:
  - file-system
  - shell
  - notify
inputs:
  - task: original user request
  - reason: why we're escalating ("hard_gate" | "build_failed" | "reflection_low_confidence" | "user_request")
  - context_gathered: RAG chunks, file reads, investigation done so far
  - proposed_approach: plan from decompose-plan (if any)
  - build_errors: remaining compiler errors (if build_failed)
  - critique_history: findings from reflection passes (if any)
  - files_in_scope: list of affected file paths
outputs:
  - handoff_path: path to written handoff.md
  - command: ready-to-paste claude command
  - summary: one-sentence description for user
metadata:
  openclaw:
    category: coding
    tags:
      - coding
      - handoff
      - escalation
      - claude-code
    requires_openclaw: ">=2026.3.31"
    binaries:
      - python3
---

# Claude Code Handoff

## The principle: never auto-invoke Claude

Claude Max quota is finite. Auto-invoking on every hard task burns it
unnecessarily and removes user control. This skill ALWAYS produces a file
and notifies the user — it never calls the Claude API directly.

The user reviews the handoff, decides if they want to spend quota on it,
then runs Claude Code themselves. This is the contract.

## Handoff package format

Written to `{project_root}/.openclaw-skills/handoffs/{timestamp}-{slug}.md`

```markdown
---
timestamp: 2026-04-21T14:32:18Z
task_slug: add-swiftdata-cloudkit-migration
reason: iOS domain (hard gate)
orchestrator_version: 1.0.0
local_model: m27-jangtq-crack
---

# Handoff: Add SwiftData + CloudKit migration for iOS 26

## Original request
[verbatim user request]

## Why this is being handed off
**Reason**: iOS domain hard gate

Local M2.7 JANGTQ-CRACK's Swift training data is stale on SwiftData + CloudKit
migrations for iOS 26. This is a case where Claude Sonnet 4.6's more recent
training plus 1M context beats retrieved RAG snippets.

## Context gathered locally

### Files read
- `App/AppDelegate.swift` (112 lines)
- `Models/User.swift` (48 lines)
- `Models/UserDataSource.swift` (204 lines)
- `Views/ContentView.swift` (89 lines)

### Codebase patterns identified
- Project uses SwiftData with `@Model` macro
- Existing SwiftData stack in `Models/UserDataSource.swift:42`
- No CloudKit integration yet
- Deployment target: iOS 18, need to upgrade to iOS 26 first

### Relevant Apple documentation retrieved
1. [S

_meta.json

{
  "ownerId": "kn7c2bd0k76aqthvnncn5ck475859yfw",
  "slug": "claude-handoff",
  "version": "1.0.0",
  "publishedAt": 1776779195122
}

skill-card.md

## Description:

Writes a structured handoff package when a local agent determines cloud Claude Code is needed, while leaving Claude Code execution under user control.

This skill is ready for commercial/non-commercial use.

## Publisher:

[stephenlthorn](https://clawhub.ai/user/stephenlthorn)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and coding agents use this skill to prepare a structured Claude Code handoff when local work reaches an escalation gate, build-failure limit, low-confidence review, context limit, or explicit user request. It captures task context, local findings, a proposed plan, and a ready-to-run command so the user can review the handoff before spending Claude Max quota.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Generated handoff files can contain task details, project context, file paths, build errors, and other sensitive development information.

Mitigation: Review the generated Markdown handoff for secrets, proprietary details, and unnecessary context before sending it to Claude Code.

Risk: Notification behavior can transmit handoff metadata when OPENCLAW_NOTIFY_ENDPOINT is configured.

Mitigation: Unset OPENCLAW_NOTIFY_ENDPOINT or restrict it to a trusted endpoint before using the skill in sensitive projects.

Risk: The ready-to-paste shell command includes the project path and should be treated carefully for projects with unusual or untrusted path names.

Mitigation: Inspect and edit the command before running it, especially when the project path was created from external input.

Risk: The skill writes local status and handoff-log files that may preserve metadata after the handoff is complete.

Mitigation: Review retention expectations for .openclaw-skills files and remove local handoff or log artifacts when they are no longer needed.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/stephenlthorn/skills/claude-handoff)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown handoff file with a ready-to-paste shell command and short text summary]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Writes a local handoff file under .openclaw-skills/handoffs and may write local notification and handoff-log files.]

## Skill Version(s):

1.0.0 (source: frontmatter and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular