dsh-collatz
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-collatz
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-collatz in your DeepSeek Harness terminal to install this Collatz sequence plugin; source code is available at https://github.com/uckkk/dsh-collatz
About this plugin
The Collatz conjecture remains one of the simplest unsolved problems in mathematics: halve an even number, triple-and-add-one an odd one, and repeat until (conjecturally) you reach 1. dsh-collatz turns this deterministic computation into a native tool inside DeepSeek Harness sessions, so the model can execute sequence iterations directly in conversation without scripting or external calls.
The entire plugin is written in pure Node with zero network dependencies and zero third-party runtimes. It runs reliably in fully offline sandboxes, intranet deployments, or resource-constrained edge devices, immune to network jitter. For inference, a single tool call returns the full iteration path and step count, ready to consume.
It suits two audiences: math enthusiasts and educators who want to verify Colatz trajectories on the fly or compare convergence lengths across starting values; and developers working in offline or intranet environments who need to attach a deterministic computation tool to their LLM without browsers or remote APIs.
Use Cases
- Verify Collatz iteration paths and step counts for any positive integer in conversation
- Attach a deterministic math tool to an LLM in fully offline sandboxes
- Compare convergence lengths across starting values in intranet environments
Best For
- Math enthusiasts and teaching demonstrations
- Application developers in offline or intranet environments
- Inference deployments on resource-constrained edge devices
Related Plugins
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.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.