Preface

The DeepSeek Harness (DSH) plugin ecosystem aims to extend agent capabilities through code. When an agent needs to return deterministic results based on fixed rules (for example, calculations for specific business logic), rather than relying on online search, a pure Node implementation is a lighter choice. dsh-watering-schedule is such a tool: it does not require network requests and returns suggestions locally based on parameters.

Plugin Overview

This is a plugin maintained by uckkk that provides watering frequency recommendation functionality. It is implemented in pure Node.js, does not depend on any external network interfaces, and runs within the local permissions of the DSH process.

Core Features

  • Watering frequency recommendations: Returns deterministic watering frequency recommendations based on input parameters.
  • Parameter-driven: Controls output results through parameters; the logic is self-contained.
  • No network dependencies: Pure local computation with high execution efficiency.

Installation and Activation

Before installation, ensure that DeepSeek Harness and its dependency environment are installed. The versions must meet the following peerDependencies requirements:

  • @deepseek-ai/cordis >= 4.0.1
  • @deepseek-ai/dsh-tools >= 0.1.0-rc.6

Run the following command in the terminal to install the plugin:

dsh plugin add github:uckkk/dsh-watering-schedule

After installation is complete, the plugin will be loaded automatically and register the corresponding tools in the session.

Typical Usage

After successful installation, directly call the tool registered by the plugin in the session to obtain watering frequency recommendations.

Applicable Scenarios and Notes

This plugin is suitable for scenarios that require deterministic logical output. Because it runs with DSH process permissions, it is recommended to inspect the source code before installation to ensure compliance with security standards. The license is MIT.

Conclusion

dsh-watering-schedule provides a lightweight local logic processing solution for the DSH ecosystem. For more details and source code, refer to the following links: