dsh-sort
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-sort
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-sort in DeepSeek Harness to install this plugin; the source is available at https://github.com/uckkk/dsh-sort
About this plugin
During model-inference sessions you often need to sort an array of values, yet there is rarely a lightweight, plug-and-play local tool at hand. dsh-sort fills exactly that gap: it wraps array sorting into a tool you can invoke directly inside the conversation, so you do not have to wire up extra infrastructure yourself.
The design philosophy is deliberately minimal. It is a pure Node.js implementation with zero network dependencies and no external services or runtime frameworks. Once the plugin is installed, the tool is registered into the current session automatically; you simply call it in the dialogue and the sorted result comes back instantly, all processed locally so your data never leaves the machine.
If you are building conversational workflows that frequently require local array sorting and want to avoid heavyweight dependencies or remote APIs, dsh-sort is a suitably light and fast option: MIT-licensed, ready to use out of the box, and out of the way the moment you are done.
Use Cases
- Sorting a batch of values on the fly during a model-inference session
- Adding local array-sorting capability to a conversational workflow
- Handling lightweight sorting tasks without heavyweight dependencies
Best For
- Model-inference developers who need local array sorting
- Tool users who want zero network dependencies and plug-and-play usage
- Engineers building lightweight conversational workflows
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.