dsh-gross-margin
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-gross-margin
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-gross-margin in DeepSeek Harness to install the plugin; the full source repository is at https://github.com/uckkk/dsh-gross-margin.
About this plugin
In model-inference or multi-step analysis pipelines, gross margin calculation looks trivial, yet it often becomes a friction point when you lean on external APIs that add network latency and unpredictable failure modes. dsh-gross-margin moves that step entirely on-device so every link in your reasoning chain stays instant, offline-capable, and reproducible.
The plugin registers a local tool called gross_margin that accepts structured parameters, computes the margin with full precision, and returns a detailed result broken down by calculation step. The entire implementation is pure Node.js with zero network dependency, so there are no third-party services, no extra runtimes, and no configuration beyond calling the registered tool.
If you are building a DeepSeek Harness reasoning chain that needs an embedded financial metric, or simply want a deterministic gross-margin step inside a larger multi-stage analysis, this lightweight plugin fills that gap cleanly. Released under the MIT license, it is free to integrate into any project without restriction.
Use Cases
- Embedding a financial metric step in multi-step reasoning chains
- Running deterministic gross margin calculations in offline environments
- Quickly returning detailed results in business analysis workflows
Best For
- Developers building DeepSeek Harness reasoning chains
- Analysts requiring zero-network-dependency financial calculations
- Plugin integration engineers seeking lightweight, ready-to-use tools
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.