Skip to main content

GitHub Copilot's starts supporting AGENTS.md: A step toward unified AI Instructions

The AI coding assistant landscape has been quietly wrestling with a fragmentation problem. If you're working with multiple AI tools, you've likely noticed the proliferation of instruction files cluttering your repositories: .cursorrules for Cursor, CLAUDE.md for Claude, .github/copilot-instructions.md for GitHub Copilot, and more. Each tool requires its own special configuration file, creating maintenance overhead and scattered documentation.

Enter AGENTS.md, a simple, open format for guiding coding agents.

GitHub's recent introduction of AGENTS.md support in their Copilot coding agent marks an important next step toward solving this problem.

What's new with AGENTS.md

With this announcement GitHub Copilot's autonomous coding agent now recognizes AGENTS.md files in your repositories. This file format allows you to provide custom instructions that guide Copilot on understanding your project structure, coding conventions, and how to build, test, and validate changes.

The implementation is thoughtfully designed with flexibility in mind:

  • Single root file: Create one AGENTS.md at your repository root for project-wide instructions
  • Nested configurations: Place AGENTS.md files in subdirectories to provide context-specific guidance for different parts of your codebase
  • Backward compatibility: Copilot continues to support existing formats including .github/copilot-instructions.md, .github/instructions/**.instructions.md, CLAUDE.md, and GEMINI.md

I think this marks an important milestone in AGENTS.md becoming the de facto standard for AI agent instructions, making life easier for developers and creating a cleaner, more maintainable approach to configuring our AI collaborators.

So go and start making the switch!

More information

AGENTS.md

Copilot coding agent now supports AGENTS.md custom instructions - GitHub Changelog

Labels:

Popular posts from this blog

Azure DevOps/ GitHub emoji

I’m really bad at remembering emoji’s. So here is cheat sheet with all emoji’s that can be used in tools that support the github emoji markdown markup: All credits go to rcaviers who created this list.
Read more

Kubernetes–Limit your environmental impact

Reducing the carbon footprint and CO2 emission of our (cloud) workloads, is a responsibility of all of us. If you are running a Kubernetes cluster, have a look at Kube-Green . kube-green is a simple Kubernetes operator that automatically shuts down (some of) your pods when you don't need them. A single pod produces about 11 Kg CO2eq per year( here the calculation). Reason enough to give it a try! Installing kube-green in your cluster The easiest way to install the operator in your cluster is through kubectl. We first need to install a cert-manager: kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.14.5/cert-manager.yaml Remark: Wait a minute before you continue as it can take some time before the cert-manager is up & running inside your cluster. Now we can install the kube-green operator: kubectl apply -f https://github.com/kube-green/kube-green/releases/latest/download/kube-green.yaml Now in the namespace where we want t...
Read more

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