AI Agent Hub
Back to plugins
🖥️

dsh-line-select

Client Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install fengMax1997/dsh-line-select

Paste the following prompt into your AI chat to install this plugin:

To install this plugin in DeepSeek Harness, please use the command line to run the installation instruction or visit the GitHub repository link:. Source: https://github.com/fengMax1997/dsh-line-select

About this plugin

In conversational code editing scenarios, precisely locating and modifying specific code segments can be a challenge. Manually copying and pasting large blocks of text is prone to errors, and relying solely on text input for line numbers lacks intuitiveness. dsh-line-select aims to solve this problem by deeply integrating file browsing with line selection capabilities, allowing users to interact with files and code intuitively.

This plugin offers robust file tree browsing and line-numbered code preview features. Users can not only view the workspace directory structure within the panel but also easily select line ranges by clicking on line numbers, generating standard reference formats like @src/app.ts:10-50. This ensures that when the Agent sends a message, it can precisely obtain the original text of the specified line range without having to read the file itself, significantly improving the accuracy and efficiency of code modifications.

This is an ideal tool for proxy engineers and developers who require fine-grained control over code context. By seamlessly integrating file selection into the input stream, it optimizes the workflow, preventing token overflow caused by stuffing large file contents into the context while ensuring the AI model receives the accurate code snippets needed for modification.

Use Cases

  • Modifying specific code blocks
  • Quickly previewing code file contents
  • Precisely injecting code context into the Agent

Best For

  • Developers using AI Agents for coding assistance
  • Users needing fine-grained control over code context ranges
  • Users who prefer visual interaction with files and code