Skip to main content

Github Copilot on the command line

In my continuous journey to become an AI native developer, I reserve some time every day to discover new tools and try new ways of working. Today I decided to give the new Github Copilot CLI a try.

As developers we spend a significant portion of our day in the terminal. Cloning repositories, installing dependencies, debugging issues, running builds, and navigating codebases—all without leaving the command line. But when you needed AI assistance from Github Copilot, you had to break your flow and switch to your editor or browser.

Other AI vendors like Claude Code even offers a command line first experience, but a similar experience for Github Copilot was missing. Until now.

What is GitHub Copilot CLI?

GitHub Copilot CLI brings AI-powered assistance directly to your terminal. It's a command-line tool that lets you leverage the power of GitHub Copilot without ever leaving your shell. No context switching, no workflow interruptions—just you, your terminal, and an intelligent assistant ready to help.

So far I’ve mostly used AI assistance inside an IDE, so I’m curious to find out how the experience is like.

Getting started is simple

Setting up Copilot CLI takes just a few minutes:

  • Install via npm: npm install -g @github/copilot
  • Launch: Run copilot in your terminal
    • Copilot ask if it could trust the folder I’m running the command from. Let’s go for option 2 and hit Enter.

  • Authenticate: Use /login to sign in with your GitHub account
    • Open your browser and enter the one-time code.
    • You also need to confirm to which organisations it has accces to.

 

That's it. No API keys to manage, no complex configuration. If you have a GitHub Copilot Pro, Pro+, Business, or Enterprise plan, you're ready to go.

Requirements: Node v22+ and npm version 10 or later

Time for a simple prompt to get some feedback about our codebase:

And about a specific file:

Let’s explore some features

Editing a file

You can ask Copilot to edit files through the CLI and approve changes. Probably something where I still would prefer to use the IDE but usable to review some changes.

 

Slash commands and file mentions

A first nice feature I noticed is that you don’t need to remember the commands as the CLI provides autocompletion when hitting ‘/’:

Also if you want to point the CLI to a specific file, the list of files in your directory is shown when hitting ‘@’:

This already makes the command line experience a lot better and brings it close to what we are used in our IDE.

Directory control

As already mentioned in the Getting Started, you have direct control on the folders trusted by the Copilot CLI.

You can see the list of trusted directories using the /list-dirs command:

And add a new directory through the /add-dir command.

What’s next?

There is a lot more to explore, let’s continue tomorrow with a follow-up post. Stay tuned!

More information

GitHub Copilot CLI: How to get started - The GitHub Blog

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