LESSON · 1 OF 4

Inside the console

Inside the console

Headless mode answers once and leaves. The interactive console - launched by just typing claude - is where you work with the agent: a conversation that keeps context, shows you diffs before they land, and asks permission as it goes.

Slash commands

Inside the console, lines starting with / are commands, not prompts:

CommandWhat it does
/initAnalyzes the project and writes CLAUDE.md - the project memory Claude reads every session
/modelSwitches models mid-conversation (opus, sonnet, haiku)
/helpLists everything else
/exitLeaves the console (Ctrl+C twice also works)

The one habit that matters

Always launch claude from the project directory. The console works relative to where you started it: that's where /init writes CLAUDE.md, and the files it reads and edits are resolved from there.

Which model, when

/model is a power dial: haiku for quick questions, sonnet for everyday work, opus for the hard problems. In this lab those are real Claude models, and switching mid-conversation is free to try.

Next, create a project and let /init document it.


Your lab setup

This VM comes with Claude Code preinstalled and signed in - just run claude to start.

Spin up a fresh environment and practice live.
claude-code-ubuntu · fresh machine · ready in under a minute