dsh-sum-of-divisors
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-sum-of-divisors
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-sum-of-divisors in your terminal to install the plugin; the full source lives at https://github.com/uckkk/dsh-sum-of-divisors .
About this plugin
When prompting a language model on number-theory tasks such as finding the sum of all positive divisors of n, the model can slip on enumeration, dropping a factor or double-counting one, making results hard to reproduce. dsh-sum-of-divisors turns that step from self-computation into a deterministic tool call, removing one source of error from the reasoning chain.
Under the hood it is a pure Node.js implementation with zero network dependencies. Once installed it registers as an in-conversation tool, so it runs reliably in offline environments or pipelines where external API calls are unavailable or undesirable.
It is well suited to developers building math or number-theory agents, evaluation harnesses, or inference chains that benefit from offloading deterministic arithmetic to a utility function, leaving model capacity for the reasoning and explanation that actually require it.
Use Cases
- Compute sum of divisors accurately in number-theory reasoning without missed or duplicated factors
- Invoke deterministic arithmetic sub-tasks in fully offline environments
- Decouple precise calculation from the model when building math agents
Best For
- Developers building number-theory or math-related agents
- Engineers running offline inference pipelines with no external dependencies
- Researchers designing model evaluation sets that need deterministic baseline functions
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.