dsh-exposure-calc
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-exposure-calc
Paste the following prompt into your AI chat to install this plugin:
Install this exposure-combination plugin in DeepSeek Harness by running dsh plugin install uckkk/dsh-exposure-calc; the source code is available at https://github.com/uckkk/dsh-exposure-calc .
About this plugin
In model-inference workflows, exposure-combination calculations often depend on external services or ad-hoc scripts, making them fragile and hard to reproduce. dsh-exposure-calc packages this step into a ready-to-use local tool: call the registered tool in your session, pass in the parameters, and receive an exact, detailed result—no more writing throwaway scripts for every run.
The plugin is implemented entirely in pure Node.js with zero network calls. All computation runs locally, so it fits naturally into offline environments, CI pipelines, and data-privacy-sensitive contexts. There are no API keys to manage and no remote services to maintain; you install and go.
If you keep hand-assembling exposure parameters or scripting combination math on the fly inside your inference pipeline, this plugin collapses that repetitive work into a single, well-defined tool call. The calculation step becomes more reproducible, easier to audit, and straightforward to integrate into your existing workflow.
Use Cases
- Precise exposure combination math inside an inference pipeline
- Offline or sandboxed computation with zero network calls
- Replacing one-off exposure scripts with a reusable tool call
Best For
- ML inference pipeline engineers
- Developers working in offline or restricted environments
- ML engineers who value reproducible, auditable computation
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.