wxxb789

Dsh Legion

Name: Dsh Legion
Author: wxxb789

AI community

SOURCE https://github.com/wxxb789/dsh-legion

Description

Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent profiles, exact model routes, declarative teams and strategies, and bounded subagent delegation - a TypeScript plugin that adds no second runtime.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

dsh-legion: Multi-Agent Orchestration and LLM Model Routing for DeepSeek Harness

**English** · [简体中文](README.zh-cn.md)

[![CI](https://github.com/wxxb789/dsh-legion/actions/workflows/ci.yml/badge.svg)](https://github.com/wxxb789/dsh-legion/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) [![Node.js](https://img.shields.io/badge/Node.js-%5E22.19.0%20%7C%20%3E%3D24.0.0-339933?logo=node.js&logoColor=white)](package.json) [![TypeScript](https://img.shields.io/badge/TypeScript-strict-3178C6?logo=typescript&logoColor=white)](tsconfig.json) [![DSH plugin](https://img.shields.io/badge/DeepSeek%20Harness-dsh--plugin-5b4ee5?logo=github&logoColor=white)](https://github.com/topics/dsh-plugin)

**dsh-legion** is a TypeScript multi-agent orchestration plugin for [DeepSeek Harness (DSH)](https://github.com/deepseek-ai/deepseek-harness). It turns one AI coding agent into a bounded orchestration cohort: configurable AI agent Specialists, an exact LLM model router, declarative Cohorts and Strategies, structured results, and depth-limited subagent delegation — without replacing the DSH runtime.

TL;DR

What it is. A DeepSeek Harness plugin for multi-agent delegation policy — not a standalone agent framework.
What it adds. One model-facing legion tool whose choices are semantic Specialists such as quick, deep, and review. Each Specialist carries a deployment-owned model route, subagent backend, persona, tool filter, depth, and result contract.
Why it helps. The coordinating agent picks intent instead of model IDs, a prompt can never widen t