dsh-log-any
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-log-any
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-log-any in DeepSeek Harness to install this plugin; the source code is available at https://github.com/uckkk/dsh-log-any
About this plugin
When a model-inference or data-processing pass calls for a quick logarithm with an arbitrary base, reaching for an external calculator or writing throwaway code is a needless interruption. dsh-log-any turns that step into a single tool call: once installed, the plugin registers a function in your session, and you simply supply the base and the argument to get the result back.
The implementation is pure Node with zero network calls or external services, so it works just as well in fully offline setups and adds negligible latency.
It fits workflows where logarithmic arithmetic shows up repeatedly inside a reasoning chain — information-entropy math, decibel conversions, scientific-computation helpers, and the like. If you want to fold these basic math operations directly into your conversational pipeline and reduce context switches, this lightweight plugin fills that gap.
Use Cases
- Computing information entropy or decibel conversion mid-reasoning
- Grabbing an arbitrary-base logarithm on the fly in an offline setup
- Weaving quick math ops into a conversational pipeline without context switches
Best For
- Developers who hit exp/log ops frequently during inference
- Users who prefer zero-dependency, fully offline tooling
- Engineers embedding lightweight math into their session 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.