dsh-range
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-range
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-range in the DeepSeek Harness terminal to install this plugin; full source: https://github.com/uckkk/dsh-range.
About this plugin
In a model-inference pipeline, range generation is a small but essential step: you need to define output bounds or parameter intervals without dragging in extra network calls or heavyweight runtime dependencies. dsh-range is built exactly for this small and deterministic job. It packages range generation into a plug-and-play session tool, so it is ready the moment you install it, with no environment setup and no remote services to pull.
The tech stack is deliberately minimal: pure Node.js, zero network dependencies, meaning it runs entirely offline on your machine. After installation, the plugin registers a tool into your session automatically; you simply invoke it in conversation to complete a range generation, with no middleware or bridge layers in between.
If you prefer lightweight, offline-capable inference tooling, or you are assembling a local pipeline that does not depend on external APIs, dsh-range is a clean fit: MIT-licensed, transparent code, and no hidden network requests.
Use Cases
- Generating parameter ranges or output bounds in fully offline environments
- Quickly defining model input and output intervals within a local pipeline
- Computing range constraints without any external API dependency
- Invoking a range-generation tool directly in session with zero extra setup
Best For
- Developers who prefer local, offline inference and want to avoid network dependencies
- Engineers assembling lightweight model-inference pipelines
- Node.js users who need a plug-and-play range generation tool with zero setup
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.