dsh-cone
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-cone
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-cone in the DeepSeek Harness terminal to install the plugin; the source lives at https://github.com/uckkk/dsh-cone, and once installed you can invoke its registered tools directly in any session to perform cone computations.
About this plugin
When a cone geometry calculation comes up inside an agent session or a multi-step pipeline, you normally have to break out of the flow, open a separate calculator, or work through the formula by hand. dsh-cone packages that computation as a tool you can invoke right within the conversation, so the result arrives without leaving your current context.
The implementation stays deliberately lean: pure Node.js, zero network dependencies, no extra runtime and no external API to reach. Once the plugin loads it registers its tool automatically, and a single call returns the result with no added latency or state-management overhead, making it a natural fit for any orchestration chain on the dsh runtime.
If you find yourself reaching for cone-related math in teaching assistants, quick engineering estimates, or multi-tool agent workflows, dsh-cone offers a light, fast drop-in solution. Released under the MIT license, it is free to integrate or extend.
Use Cases
- Solving cone volume and surface area in teaching conversations
- Batch computing cone parameters in engineering estimates
- Serving as a math computation node in multi-tool agent pipelines
Best For
- Developers embedding math tools in agent sessions
- Builders of teaching assistants and Q&A bots
- Engineers orchestrating multi-tool pipelines on the dsh runtime
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.