dsh-divisor-count
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-divisor-count
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness by running dsh plugin install uckkk/dsh-divisor-count; the source repository is available at https://github.com/uckkk/dsh-divisor-count.
About this plugin
During a model-inference session, a frequent small task is counting the divisors of an integer. dsh-divisor-count keeps that calculation entirely local: it is a pure Node.js implementation with no network dependency, so you never need to call an external service or wait on a remote API just to answer a simple number-theory question.
Once installed, the plugin registers a tool into your session. When you ask the model to count divisors of a number, it invokes that local tool directly, returning the result within the same conversation turn. The implementation is straightforward: pure Node, zero network calls, zero third-party services, making it a lightweight deterministic building block inside your reasoning chain.
It suits anyone assembling a local-first inference workflow who wants to fill in basic arithmetic utilities without pulling in browser plugins or external APIs. If a one-shot divisor count is all you need, dsh-divisor-count keeps the dependency footprint as small as it gets.
Use Cases
- Quickly counting divisors of an integer inside an inference session
- Filling in a basic number-theory primitive in a local-first workflow
- Avoiding external APIs or browser plugins for a one-shot math lookup
Best For
- Developers building local-first inference pipelines with minimal dependencies
- AI engineers who need deterministic math tools callable inside a session
- Users who prefer fully offline execution and want to avoid remote services
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.