Enhancing C# Development with GitHub Copilot CLI and VS Code

GitHub Copilot is transforming how developers work by turning AI from a simple code generator into a practical development partner. In this article, we explore how to use GitHub Copilot CLI and Visual Studio Code together with the Awesome Copilot ecosystem to build better .NET applications, customize AI behavior, and bring domain-specific guidance directly into the development workflow. From designing models and applying best practices to installing reusable agents, instructions, and skills, this walkthrough shows how to make Copilot feel deeply integrated with the way you code.

Using GitHub Copilot CLI

Create a sample .NET Console app

From within a termnal window in a working directory, type the following commands:

dotnet new console -o AwesomeAthlete
cd AwesomeAthlete

Install GitHub Copilot CLI

Follow instructions at Installing GitHub Copilot CLI to install the GitGub Copilot CLI.

Start the copilot app by typing the following command inside the same folder as the .NET app created earlier:

copilot

Explore online plugins repo

Visit: https://github.com/github/awesome-copilot and review the plugins/csharp-dotnet-development plugin.

Install the plugin by entering this command in GitHub Copilot CLI:

/plugin install csharp-dotnet-development@awesome-copilot

To view a list of plugins, enter this command:

/plugin list

Let's get the plugin to do something useful. For example, ask the plugin to help you design some domain models by entering this command:

@csharp-dotnet-development help me design a class model for Athlete

Thereafter, you can enter this command to add the required C# classes:

add the class models to my app and put code in Program.cs that calls those classes and prints sample data to the console

Among others, the plugin contains a command named /csharp-dotnet-development:dotnet-best-practices. We can use this command by entering this instruction:

/csharp-dotnet-development:dotnet-best-practices

Since we have a very simple C# application, the only suggestion made by AI is to add documentation to the domain classes.

Exit GitHub Copilot CLI by typing in the /exit command.

/exit

Using Visual Studio Code (VS Code)

If you do not already have VS Code installed on your computer, you can get it from https://code.visualstudio.com/. Make sure to install the GitHub Copilot Chat extension before proceeding.

Open the AwesomeAthlete folder in VS Code. You ca do that by simply typing in the following from a termninal window from inside the AwesomeAthlete folder:

code .

Customize or Extend the Plugin

You can modify plugin components to suit your needs.

In plugin folder: ~/.copilot/installed-plugins/awesome-copilot/<plugin-name>/

• Edit com.github.copilot/agents/*.md to change agent behavior
• Edit skills/*/SKILL.md to add new skills

Restart VS Code to reload changes

Installing Awesome Copilot artifacts

Point your browser to Awesome GitHub Copilot. Let's try installing the Caveman Mode instruction that optimizes token interaction with AI. Click on Instructions.

Find the Caveman Mode instruction. Click on VS Code Install.

Click Yes on this dialog.

Choose to install the instructions in the current workspace under folder .github, instead of globally.

Accept the default name caveman-mode for the instructions.

The caveman-mode-instructions.md file is saved in your workspace under .github.

Here is an example on how to use this instruction. Enter the following into the VS Code chat window:

caveman-mode how many years did it take to build the empire state building in new york

The prompt is distilled to the essential keywords: Empire State Building construction duration. The response stays concise and focused, avoiding unnecessary wording. This keeps token usage low and saves you money.

Awesome Copilot

The Awesome Copilot (By Tim Heuer) extension for VS Code allows you to browse and download instructions, prompts, chat modes, and agents from the Awesome Copilot community.

Install the above extension into your VS Code. You wiill find Awesome Copilot in your explorer.

You will find folders Instructions, Agents, and Skills.

For example, expand the Agents node, then select CSharpExpert.agent.md.

If you decide to download this agent, click on the download tool beside it.

You can change the same of the agent .md file. Simply hit Enter to accept the default name.

The agent gets installed in your local workspace under .github/agents.

You can also modify any of these AI artifacts after you install them locally.

💡 TIP: There are new AI artifacts being added regularly. Click on refresh to load the latest.

@agentPlugins

There are multiple ways of installing AI plugins into VS Code. In your VS Code Extensions tab enter the keywoord @agentPlugins.

There are many plugins that you can choose from. You can narrow down the list by adding a filter. For example, I entered the csharp filter and received a short list of the plugings that fit that keyword:

Click on the csharp-dotnet-development plugin. You will see more information about the plugin. In this example, the plugin consists of a number of slash (/) commands and one agent.

I you are in a C# application, you can use the /csharp-dotnet-development:csharp-xunit slash command to generate test cases with this prompt:

/csharp-dotnet-development:csharp-xunit generate test cases

Plugins consist of plugin.json file, skills, agents, hooks, and MCP. Below is an illustration of the plugin architecture:

Any agents that are installed in your environment can be invoked from the chat window. For example, in the below illustration, I installed the CSharpExpert.agent.md agent locally and it is appears in the chat window ready to be invoked:

You can, at any time, disable or uninstall any plugin by right-clicking on it in the extensions tab and choosing disable or uninstall.

Conclusion

GitHub Copilot plugins extend AI-assisted development beyond simple code generation. With GitHub Copilot CLI, VS Code, and the Awesome Copilot ecosystem, you can add specialized agents, instructions, skills, hooks, and commands to your C# workflow.

These tools help you design .NET applications, apply best practices, generate tests, and customize Copilot to match your development style. Explore the available artifacts, install the ones that fit your needs, and adapt them to make GitHub Copilot a more effective development partner.

References

Manage Agents, Instructions, Prompts, & Skills in Seconds with this VS Code Extension

Get Awesome-Copilot custom chat modes and prompt files - right from within GitHub Copilot Chat.

GitHub Copilot Agent Plugins: Package & Distribute Skills, MCP, Hooks & Custom Agents