DeepSeek Harness Plugin

dsh-std

Tools & Capabilities 156 stars DSH Plugin

@dsh-std/core is a "meta-protocol" (the protocol about protocols ).

Plugin facts

GitHub stars 156
LicenseMIT
Primary languageTypeScript
Last push2026-10-10T03:01:01Z
MaintainerT-Auto
Added to this directory2026-10-03

Screenshots

Install this DSH plugin

Copy the command below and run it in your DeepSeek Harness terminal.

dsh plugin add github:T-Auto/dsh-std

Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →

More about this plugin

Domain-specific protocols—like Command, Tool, Model, and Presentation—sit on top of this meta-protocol substrate for discovery and negotiation, each versioned independently. Different hosts and applications only implement the parts they actually need.

About this plugin: dsh-std

What is dsh-std?

dsh-std is a tools & capabilities plugin maintained by T-Auto. @dsh-std/core is a "meta-protocol" (the protocol about protocols ).

How do I install dsh-std?

Run dsh plugin add github:T-Auto/dsh-std in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:T-Auto/dsh-std#commit.

Is dsh-std free?

dsh-std is a community open-source project released under the MIT license. You can inspect its source and install it for free.

modlens

Featured 4226

Tools & Capabilities

The first vision plugin for DeepSeek Harness, and a vision bridge for text-only coding agents. Paste an image and receive structured JSON evidence back — OCR, layout, and semantic understanding — ready for any agent to act on.

View plugin → liustack GitHub profile image liustack

billion-context

Featured 1102

Tools & Capabilities

Model-Driven Incremental Hierarchical Compression: Training-Free Multi-Generational Context Management for Long-Lived Coding Agents (English, v0.2) 📝 The paper itself is…

View plugin → ranxianglei GitHub profile image ranxianglei