Claude Code is an AI coding agent that lives in your terminal. You give it a goal in plain language and it plans, runs commands, reads and edits files, and reports back - the same loop a human engineer runs, automated.
| Mode | Command | When |
|---|---|---|
| Interactive console | claude | Working on a task together, back and forth |
| Headless (print mode) | claude -p "prompt" | Scripts, pipelines, one-shot answers |
Headless mode is the one that composes with everything else on Linux. Its answer goes to stdout, so you can pipe it, redirect it, or call it from cron.
This VM has Claude Code preinstalled and signed in with your Claude account,
so you can start working right away. You can pick which model answers with
/model - opus for hard problems, sonnet for everyday work, haiku for quick
questions. Nothing to configure.
By default Claude asks before it touches your files or runs commands. In
headless mode you grant that up front with --permission-mode acceptEdits
(file edits allowed), and you stay in charge of everything else.
Next, verify the prerequisites on this machine.
Your lab setup
This VM comes with Claude Code preinstalled and signed in - just run claude to start.