The core philosophy of DeepSeek Harness (DSH) is “everything is a plugin,” allowing developers to flexibly integrate domain-specific capabilities. When building agents involving fitness, sports science, or numerical computation, estimating 1RM (one-repetition maximum) is often a necessary calculation step. The dsh-one-rep-max plugin provides this calculation capability to DSH.

Plugin Positioning and Features

The plugin is maintained by the user uckkk and is designed to meet the immediate calculation needs of agents when processing fitness data. Core features include:

  • 1RM Estimation: Supports precise calculation based on parameters and returns detailed results.
  • No Network Dependency: Implemented purely in Node, without relying on external network interfaces, ensuring calculations can be completed locally.

Installation and Enablement

Install the plugin in a DSH environment using the following command:

dsh plugin add github:uckkk/dsh-one-rep-max

Usage

After installation, the plugin registers the corresponding tools in the session. Developers or agents can directly call these registered tools in subsequent conversations or tool calls to perform 1RM estimation.

Use Cases and Precautions

  • Use Cases: Suitable for agent scenarios that require quick local 1RM calculations and demand accuracy in the results.
  • Precautions:
    • The plugin runs with the permissions of the current DSH process. Please review the source code and license before installation.
    • Dependencies must satisfy @deepseek-ai/cordis (^4.0.1) and @deepseek-ai/dsh-tools (>=0.1.0-rc.6).

Summary

dsh-one-rep-max provides lightweight 1RM estimation capability. Its pure Node implementation avoids network overhead and is suitable for offline use or environments with modest network stability requirements. For more details and source code, refer to the catalog and repository links below.