In our previous post, we have explained how to use GitHub Copilot Agent mode in VS Code.
In this post, we will show you how to extend Copilot Agent’s capabilities by using its special features to automate tasks and speed up development.
As we know, GitHub Copilot Agent is an autonomous AI developer to which you can assign tasks or issues. It runs as an integrated member of your GitHub repository and can write code, fix issues, comment on issues, open PRs, perform code reviews, and more. It can handle complex tasks, add features, and even use Model Context Protocol (MCP) tools to work with different cloud services.
Also, read:
- How To Use GitHub Copilot Agent Mode in VS Code
- How to Start with GitHub Copilot AI Tools in VS Code
So, if you’re using Copilot Agent in VS Code, you can follow these steps to enhance how you use it:
Customize AI responses in VS Code
Generally, we repeatedly provide chat prompts in Copilot Agent, and the agent generates code based on the given prompt. Instead of adding the same details in every chat prompt, we can store our requirements in files and automatically include them in every chat request.
Below are three main ways to customize AI responses in Visual Studio Code:
1. Create Custom instructions
If you have specific coding and style preferences, you can define custom instructions or rules to guide Copilot’s behavior. These can cover how to write code, add comments, perform code reviews, or generate commit messages.
There are several ways to define custom instructions for Copilot Agent in VS Code:
Create .github/copilot-instructions.md File
In this file, you can describe your code-generation instructions in Markdown. Combine all relevant instructions into a single file stored within your workspace. These instructions will be automatically included in every chat request.
Create .instructions.md files File
If you want task-specific code generation, you can create one or more .instructions.md files and describe the instructions in Markdown. These files can be stored in your workspace or user profile. You can also use glob patterns to automatically include certain instructions for all requests or only for specific files.
Specify custom instructions in VS Code settings
If you want to define instructions for tasks other than code generation, you can add them to your VS Code user or workspace settings. These settings can apply to code generation, test generation, commit messages, code reviews, and PR titles/descriptions.
The following is sample of custom instructions file to use in VS Code:
--- applyTo: "**" --- # Project general coding standards ## Naming Conventions - Use PascalCase for component names, interfaces, and type aliases - Use camelCase for variables, functions, and methods - Prefix private class members with underscore (_) - Use ALL_CAPS for constants ## Error Handling - Use try/catch blocks for async operations - Implement proper error boundaries in React components - Always log errors with contextual information
2. Use Prompt File
You can create prompt files for performaing common tasks like generating code or performing a code review. You can define the prompt content in Markdown file. A prompt file is a standalone prompt that you can run directly in chat. You can also include guidelines about how the task should be performed.
You can create prompt file .github/prompts in folder of the workspace. Here is smaple propmt file:
--- mode: 'ask' model: Claude Sonnet 4 description: 'Perform a REST API security review' --- Perform a REST API security review and provide a TODO list of security issues to address. * Ensure all endpoints are protected by authentication and authorization * Validate all user inputs and sanitize data * Implement rate limiting and throttling * Implement logging and monitoring for security events Return the TODO list in a Markdown format, grouped by priority and issue type.
Automate Code Review and PRs
Instead of having just one synchronous agent in VS Code, you can now run multiple agents simultaneously, working on your behalf—this is what being a 10x developer looks like.
To try this in VS Code, install the GitHub Pull Requests extension and add the following to your VS Code settings:
"githubPullRequests.codingAgent.uiIntegration": true,
With the GitHub Pull Requests extension, you can assign any issue to the Copilot Coding Agent directly from the sidebar—no need to switch to your browser. Just select, assign, and let the agent handle it.
Once the agent is done, it will assign the PR to you and request your review. If applicable, it will even include a screenshot so you can quickly verify its work.
You can review the agent’s PR, leave comments, and request changes—all within VS Code. The agent will then process your feedback, update the PR, and notify you when it’s complete.
5. Final Words
In this post, we explained a few special features of GitHub Copilot Agent in VS Code and how to leverage them to speed up development. You can also check out the GitHub Copilot Agent documentation page for detailed instructions on using all the features that suit your needs.