The difference that matters
A chat assistant is a very good autocomplete that cannot see your project. Claude Code is the same model wired into your machine: it can list a directory, read a file, run npm test, and write changes to disk.
That is the whole appeal, and also the whole risk. Everything else in this guide is about the second half of that sentence.
01 · Install it
Pick one. The native installer keeps itself up to date in the background; the package managers do not.
curl -fsSL https://claude.ai/install.sh | bashirm https://claude.ai/install.ps1 | iexOr through a package manager, if you would rather:
brew install --cask claude-code
winget install Anthropic.ClaudeCodeCheck it landed:
claude --versionThat prints a version number followed by (Claude Code). Homebrew and WinGet installs do not auto-update — run brew upgrade claude-code or winget upgrade Anthropic.ClaudeCode yourself now and then.
02 · Log in
Start it once and it walks you through authentication in the browser:
claudeYou can sign in with a Claude subscription (Pro, Max, Team or Enterprise), a Claude Console account with pre-paid credits, or an enterprise cloud provider. Credentials are stored, so this is a one-time step. To switch accounts later, type /login inside a running session.
03 · Your first session
Claude Code works inside a directory. Go to a project and start it there — that directory is what it can see.
cd /path/to/your/project
claudeDo not start by asking it to build something. Start by asking it to explain something, because that tells you how much it actually understands:
what does this project do?
where is the main entry point?
explain the folder structureYou do not have to paste files in or add them to context by hand. It reads what it needs as it goes.
04 · Your first change
Now give it something to do:
add a hello world function to the main fileIt finds the file, shows you the change, and depending on the permission mode either asks first or just does it.
Permission modes decide how often you are asked.
On Pro, Max and Team plans, interactive sessions start in Auto mode: a classifier reviews actions instead of you, and most edits and commands run without a prompt. On other plans they start in Manual mode, where you approve things yourself.
Press Shift+Tab at any time to cycle modes. If you are pointing it at something you care about, start stricter than you think you need to.
05 · The commands worth memorising
Two kinds: shell commands that start a session, and slash commands you type inside one.
| Command | What it does |
|---|---|
| claude | start an interactive session |
| claude "task" | start with the first prompt already typed |
| claude -p "query" | run one query, print the answer, exit — good in scripts |
| claude -c | continue the most recent conversation in this directory |
| claude -r | pick a previous conversation to resume |
| /help | list the commands available to you |
| /clear | clear the conversation and start fresh |
| /context | show what is actually loaded into context right now |
| /exit | leave (or Ctrl+D twice) |
Type / on its own to see every command and skill available in this project.
06 · What it can reach
The working directory you launched it in, and what your user account can touch from a shell. That is a bigger surface than most people picture the first time.
Any file under the directory you started it in, without asking you to attach anything.
the projectShell commands, with your permissions. Tests, builds, git, package installs.
your accountEdits files in place and creates new ones.
on diskWhich is why the next three steps of this guide exist: telling it about your project so it stops guessing, and putting guardrails on so the things you never want touched stay untouched.
Getting unstuck
- Be specific. “Fix the login bug where users see a blank screen after wrong credentials” beats “fix the bug”.
- Let it look before it leaps — ask it to analyse the schema before asking it to change anything.
- Break big asks into numbered steps; it follows a list well.
- ↑ for history, Tab to complete a command,
/helpwhen lost.
Verified against the official Claude Code documentation, September 2026. Claude Code moves quickly, so check the official documentation before relying on a detail here.