claude-delegate

Distribute CC-dispatched tasks to Claude with reverse invocation and verdict signaling.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/isaenter/UES-PRO --skill claude-delegate-isaenter
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-delegate
Source: https://github.com/isaenter/UES-PRO/tree/main/frontend-vben/.codex/skills/claude-delegate
Command: npx skills add https://github.com/isaenter/UES-PRO --skill claude-delegate-isaenter

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables seamless distribution of CC-dispatched tasks to Claude and supports reverse Claude invocations for automated review workflows in CC environments.

Core Features & Use Cases

  • Task intake & delegation: Receives CC-dispatched tasks and forwards them to Claude for evaluation.
  • Reverse-call workflow: Enables Claude to re-enter the host workflow via clean, sandboxed invocations.
  • Verdict signaling: Enforces a simple verdict protocol using VERDICT: APPROVED or VERDICT: REVISE to close cycles.

Quick Start

Submit a CC-dispatched task to Claude and observe the verdict signal to determine next steps.

Frequently Asked Questions about claude-delegate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I delegate CC tasks to Claude for code review?

To delegate CC tasks to Claude for code review, submit the dispatched task to the claude-delegate skill, which forwards it to Claude within a read-only sandbox and returns a structured verdict signal.

What is a reverse Claude call in an AI workflow?

A reverse Claude call enables Claude to re-enter the host workflow via clean, sandboxed invocations, allowing automated review processes to close cycles and signal verdicts back to the dispatcher.

How does the verdict protocol work for automated code moderation?

The verdict protocol enforces a simple signaling mechanism using VERDICT: APPROVED or VERDICT: REVISE, determining the next steps in the code review workflow based on Claude's evaluation.

Can I use a read-only sandbox for Claude code review tasks?

Yes, claude-delegate operates within a read-only sandbox to enforce safe boundaries, ensuring Claude can evaluate code and provide judgments without modifying the original files.

Does claude-delegate require any external dependencies?

No, claude-delegate runs without external dependencies or components, functioning independently to distribute tasks and manage reverse Claude invocations within your environment.

Why does my automated review workflow need a reverse invocation path?

A reverse invocation path is needed to enable Claude to re-enter the host workflow and deliver verdicts, closing the review cycle seamlessly in automated CC environments.