Skip to content

Installation & First Steps

  • Claude Code · Module 01
  • Lesson 2 of 4 · then sources and quiz
Note
As of: November 2026

Model names, prices, and subscription limits reflect the state as of November 2026. Anthropic adjusts these regularly — check claude.ai/pricing before signing up.

Installation

Claude Code can be installed with a single command:

curl -fsSL https://claude.ai/install.sh | bash
Note
Prerequisites

You need an Anthropic account with a Pro ($20/month), Max, Ultra, Team, or Enterprise plan. Claude Code is not available on the Free plan. For API usage, an API key is required; for Pro/Max/Ultra plans, browser login is sufficient.

After installation, simply start Claude Code with:

claude

This opens interactive mode -- you can start right away and chat with Claude directly in your terminal.

Models

Claude Code uses the latest Claude models. Depending on the task, you can choose the appropriate model:

ModelIdentifierStrengthContext
Fable 5.2claude-fable-5-2Top model for the hardest and longest tasks1M Tokens
Opus 5.5claude-opus-5-5Default model in Claude Code, strong at agentic coding1M Tokens
Sonnet 5.5claude-sonnet-5-5Balanced: fast, capable, and cheaper1M Tokens
Haiku 5.5claude-haiku-5-5Fastest and most affordable model for simple tasks1M Tokens
Tip
Which Model When?

The default model is Opus 5.5 (on Pro, Max, Ultra, Team, Enterprise, and via the API). Sonnet is the cheaper choice for many everyday tasks; Fable is worth it for the hardest and longest tasks. Haiku suits simple, fast subtasks -- for example in your own subagents with model: haiku.

Pricing

Claude Code offers various access models:

  • Pro ($20/month) -- Shared with Claude Web, Desktop, and Mobile. Good for getting started, but the quota can run tight with intensive use
  • Max ($100/month) -- 5x more capacity than Pro. Recommended for regular use
  • Ultra ($200/month, formerly "Max 20x") -- 10x Pro usage per week, with no 5-hour limit for verified accounts. For power users and professional development
  • API -- Pay-as-you-go by tokens. Full cost control, ideal for CI/CD and automation
Note
Current Pricing

Prices and quotas may change. Find the latest details at claude.ai/pricing.

Permission Modes

Claude Code can perform various actions on your system -- read files, write files, execute commands. With Permission Modes, you control how much autonomy you allow:

You choose the mode at startup with --permission-mode or switch it during a session with Shift+Tab.

Manual Mode (formerly "Default")

claude --permission-mode default

Claude Code asks before critical actions -- for example, before overwriting files or executing shell commands. Ideal for getting started. In the interface, this mode is now called "Manual"; its config value is still default (manual is accepted too).

Accept Edits Mode

claude --permission-mode acceptEdits

Allows file changes automatically but still asks for shell commands. Good if you trust Claude Code with writing but want to control commands.

Auto Mode

claude --permission-mode auto

A classifier decides which actions are safe and which need confirmation. Maximum productivity with acceptable risk.

Warning
Security Note

If you are new, switch to Manual Mode with Shift+Tab (or start with --permission-mode default) and work your way up. Auto Mode is powerful, but you should first develop a feel for how Claude Code works before giving it full autonomy.

Note
Auto Mode Requirements

Auto mode is available on all plans (on Team and Enterprise, admins can turn it off). Via the Anthropic API, it works with Opus 4.6 or newer, Sonnet 4.6 or newer, Haiku 5.5, and the Fable models. From Claude Code v2.1.283 on, auto is the starting mode in the terminal and in VS Code.

First Commands

Interactive Mode

claude

The main mode. You chat with Claude Code in an interactive session. Claude sees your project directory and can read files, write files, and execute commands.

Non-interactive Mode

claude -p "Explain the architecture of this project"

Perfect for scripting and CI/CD pipelines. Claude executes the prompt and outputs the result -- without an interactive session.

Resume Last Conversation

claude --continue

Continues the last session. The entire previous context is preserved -- ideal if you interrupted a task.

Important Slash Commands

Within an interactive session, these commands are available:

CommandFunction
/helpShows all available commands
/clearClears the current context
/compactCompresses the context (saves tokens)
/initCreates a CLAUDE.md for your project
Tip
Pro Tip: /init First

Start every new project with /init. Claude Code analyzes your project and creates a CLAUDE.md file with build commands, architecture overview, and project conventions. This drastically improves all subsequent interactions.