In the plugin-based architecture of DeepSeek Harness (DSH), handling domain-specific safety rules or operational recommendations is a common requirement. Developers often need to obtain clear safety guidance based on input parameters in real time, rather than relying on the model’s own vague judgment. dsh-bleach-safety is a tool designed to support this type of scenario.
What Is It¶
dsh-bleach-safety is a tool that focuses on safety recommendations for bleaching operations. It is maintained by uckkk and belongs to the admin-security category. Its core function is to return clear safety recommendations based on input parameters.
Core Features¶
The plugin provides the bleach_safety tool. It returns clear safety recommendations based on parameters. The implementation is pure Node.js and does not rely on network requests.
Installation and Enablement¶
Use the command provided by DSH to install:
dsh plugin add github:uckkk/dsh-bleach-safety
After installation, you can directly call the tool registered by the plugin in a DSH session.
Use Cases and Notes¶
The plugin is suitable for scenarios where agent development requires integrating bleaching safety logic. Before use, ensure the environment meets the dependency requirements: @deepseek-ai/cordis (^4.0.1) and @deepseek-ai/dsh-tools (>=0.1.0-rc.6).
Note: This plugin runs with the permissions of the current DSH process. Before installation and execution, it is recommended to review the source code and license.
Summary¶
By introducing the bleach_safety tool, developers can avoid the uncertainty of the model when handling chemical operations and obtain more precise parameter recommendations. Plugin directory: https://www.skillhub.cn/plugins/uckkk/dsh-bleach-safety, GitHub: https://github.com/uckkk/dsh-bleach-safety.