dsh-leap-year
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-leap-year
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-leap-year in your terminal to install the plugin; the source code is available at https://github.com/uckkk/dsh-leap-year .
About this plugin
When large language models reason about date logic, leap-year checks are one of the most common failure points: is 2023 a leap year, how many days did February 1900 have—models occasionally get it wrong. dsh-leap-year wraps leap-year determination into a deterministic session tool, so the model can call it directly instead of relying on its own inference.
Under the hood the plugin is written in plain Node.js with zero external services and zero network calls. Once installed it registers itself as an invocable tool in the current session. The interface is straightforward: pass a year, get back a clear leap-or-not result, with no intermediate state and no external side effects.
It is well suited for developers and prompt engineers whose workflows involve frequent date arithmetic, calendar logic, or temporal reasoning. When your pipeline keeps asking the model whether a given February has 28 or 29 days, a zero-dependency tool is more reliable than a lengthy system prompt.
Use Cases
- Reliable leap-year checks when models reason about date logic
- Avoiding inference errors during batch calendar computations
- Injecting a deterministic tool call into temporal prompt pipelines
Best For
- Developers who handle frequent date arithmetic
- Prompt engineers aiming to reduce model reasoning errors
- Teams building time-sensitive automation pipelines
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.