Skip to main content

Custom chat modes in Github Copilot

Out of the box, you get 3 modes in VS Code as explained in the documentation:

Chat mode Description
Ask mode Ask mode is optimized for answering questions about your codebase, coding, and general technology concepts. Use ask mode to understand how a piece of code works, brainstorm software design ideas, or explore new technologies.
Edit mode Edit mode is optimized for making code edits across multiple files in your project. VS Code directly applies the code changes in the editor, where you can review them in-place. Use edit mode for coding tasks when you have a good understanding of the changes that you want to make, and which files you want to edit.
Agent mode Agent mode is optimized for making autonomous edits across multiple files in your project. Use agent mode for coding tasks when you have a less well-defined task that might also require running terminal commands and tools.

While these 3 modes provide solid general-purpose functionality, custom chat modes unlock the potential to create highly specialized AI assistants tailored to your specific workflows.

What are custom chat modes?

Custom chat modes are predefined configurations that combine specific instructions with curated tool sets to create focused AI assistants within VS Code. Think of them as specialized personas that your AI can adopt for different tasks - whether you're planning new features, conducting code reviews, or researching implementation approaches.

Each custom chat mode consists of:

  • Description: A brief description of the chat mode.
  • Instructions: Detailed prompts that guide the AI's behavior and responses
  • Tools: A curated set of available tools (codebase search, file operations, etc.)
  • Model selection: Choose which AI model to use for optimal results

Custom chat modes are defined using Markdown files with a .chatmode.md extension. The structure is elegantly simple:

Real world example: Beast mode

If you are looking for a real world example, I would recommend to have a look at the Beast chat mode created by Burke Holland: Introducing Beast Mode 3.1 · Burke Holland

Beast Mode builds on OpenAI’s official 4.1 cookbook coding agent example and layers in a highly opinionated workflow that is modeled after how an actual developer might work to solve a problem, implement a feature, etc. It is specifically designed to be used with GPT 4.1. Burk created this mode to fix the lack of agency and accuracy he encountered while using GPT 4.1.

You can find his markdown file here: Beast Mode

Creating your own custom chat mode

Creating your own custom chat mode is easy:

  • Open the Github Copilot Chat view

  • Select Configure Modes in the list of modes

 

  • Choose "Create new custom chat mode file"

 

  • Decide on location:
    • Workspace: Stored in .github/chatmodes/ (great for team sharing)
    • User profile: Personal modes that sync across devices

 

  • Name your mode

 

  • Start customizing…

Some example chat modes

Code Review Assistant

Create a mode focused on security, performance, and maintainability checks:

Documentation Generator

Build a mode specialized in creating comprehensive documentation:

Debugging Detective

Create a troubleshooting-focused assistant:

More information

Use chat modes in VS Code

Introducing Beast Mode 3.1 · Burke Holland

Beast Mode

Labels:

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...
Read more

Cache stampede: when our cache turned against us

While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...
Read more

A complex system designed from scratch never works

A few years ago, I worked as an architect on a big mainframe rewrite. I still count it as one of my failures. Not because the technology was wrong, but because I couldn't convince the management team to simplify the approach. Years later, the organization is still struggling to get the new system up and running. I left the project at the time, because I couldn't put my name behind an approach that would take very long and cost a lot of money without a working system to show for it along the way. Gall’s Law That memory keeps coming back to me, because it's a textbook case of Gall's Law playing out in real life. Gall's Law , from John Gall's Systemantics , states it plainly: A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works, and it cannot be patched to make it work. You have to start over with a simple system that works. What does that mean in practice,...
Read more