DeepSeek Harness (DSH) EXPLAINED | Everything Is a Plugin
Source
youtube.com
Author
Hugging Face
Date
Why it matters
It shows how DeepSeek Harness composes the agent loop, tools and system promptThe standing instructions a model receives before any user input — defining its role, rules, tools, and tone for the whole conversation.Full definition → as plugins, and how to write and load your own, including a custom loop that never calls a model.
Key takeaways · AI-distilled
In Cordis, the plugin system under DeepSeek agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition →, plugins provide services to one another, dependency injection and events connect every part of the app, and Cordis tracks each plugin's registrations so it can clean up safely when the plugin unmounts.
The video's hands-on demo runs dsh web --patch with a custom cordis.patch.yml and loads three plugins into the app: a greet tool, a bash guard and a hello plugin.
Custom plugins reach the DSH Electron desktop app as npm packages through the user's .dsh configuration, and the same mechanism can replace the agentic loopThe cycle an agent runs in: decide, call a tool, read the result, decide again — repeating until the goal is met or a stop condition fires.Full definition → with one that never calls a model.
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
agentic loop — The cycle an agent runs in: decide, call a tool, read the result, decide again — repeating until the goal is met or a stop condition fires.
system prompt — The standing instructions a model receives before any user input — defining its role, rules, tools, and tone for the whole conversation.
