Mr-potato-123

Dsh MCP — Development skill for Claude Code

Development community

dsh as mcp, make your claude code or codex etc. faster, more powerful and more economic.

How to install Dsh MCP

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Mr-potato-123/dsh-mcp and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Dsh MCP does

dsh as mcp, make your claude code or codex etc. faster, more powerful and more economic!

Alternatives in Development

Claudia — A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions 21k ★
Lamda — The most powerful Android RPA agent framework, next generation mobile automation 7.7k ★
Claude Code Rust — 🚀 Rust 全量重构的 Claude Code - 性能提升 2.5x，体积减少 97% High-performance Rust implementation of Claude Code with 2.5x f 1.4k ★

README

dsh-mcp ⚡

Fast and cheap — the heavy work runs on deepseek-v4-flash.

An execution layer for MCP agents — powered by a local DeepSeek Harness.

Agentic coding tools are expensive and slow for one reason: the parent model reads files one by one. `dsh-mcp` flips that — **the parent agent keeps the reasoning, the local DeepSeek Harness does the heavy lifting**: batch reads, edits, and command runs, priced at deepseek-v4-flash rates, on your machine.

![Platform: Windows 11](https://img.shields.io/badge/Platform-Windows_11-0078d4) ![Protocol: MCP stdio](https://img.shields.io/badge/Protocol-MCP_stdio-8A2BE2) ![License: MIT](https://img.shields.io/badge/License-MIT-blue)

**Works with any MCP client · tested end-to-end with Claude Code**

**🌐 [English](README.md) · [简体中文](README.zh-CN.md) · [日本語](README.ja-JP.md)**

Why: fast and cheap, by design

**The pain.** Long-horizon, multi-file work is where agentic tools bleed money and time: the parent model grinds through every file itself — one `Read` per file, exploration loops, context that grows and drifts. You pay the parent's per-token rates for the *reading*, and you wait for the model to do it *serially*.

**The fix.** One `delegate_to_dsh` call hands the whole token-heavy subtask to a fresh, focused DeepSeek Harness agent running **deepseek-v4-flash** inside your workspace. All the file I/O happens there — batched, local, cheap. The parent stays in the loop for what actually needs a brain: **planning, diagnosis, decisions, verification**.

Measured on 100 SWE-bench-style long-horizon tasks (heterogeneous model setup: parent = deepseek-v4-pro, DSH = deepseek-v4-flash; arm B runs the same parent model without the plugin):