32dots HEIDELBERG AI
Curriculum › GitHub Copilot course › copilot-05
Session 5 medium

Copilot in the terminal: the CLI

LESSONLesson 5 · ~20 min

🎯Goal. Bring the same assistance to the command line with the Copilot CLI.

▶ Try this prompt

Write a shell command that finds every .fasta file under this folder and counts the sequences in each.

Run Copilot CLI in your terminal and describe the task — it suggests the command and can run, test, and debug from there.

  1. 1Start the Copilot CLI in your terminal. It greets you and confirms you're logged in, then waits for a task — type ? for help or describe what you want.
  2. 2Describe a command or a job in plain English. Copilot can write, test, and debug code right from your terminal, mentioning files with @ and running / commands.
  3. 3Read each suggested command before running it. The CLI is handy for the glue work — file wrangling, quick scripts, git steps — without switching to the editor.
The GitHub Copilot CLI welcome screen in a terminal, showing the version, a logged-in user, and a prompt to enter a task
The GitHub Copilot CLI running in a terminal — it can 'write, test and debug code right from your terminal', with @ to mention files and / for commands. Source: https://github.com/features/copilot

✓You'll see. The Copilot CLI welcome screen in your terminal, ready to turn a described task into a command it can run and debug.

💳Cost. CLI features consume AI Credits (like chat and agents), so they draw on your plan's monthly Credit allowance — completions remain the only free-of-credits feature.

💡Takeaway. Copilot isn't editor-only — the CLI puts the same write-test-debug help wherever you work in the terminal.