Claude Code overview
Learn about Claude Code, an agentic coding tool made by Anthropic. Currently in beta as a research preview.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster through natural language commands. By integrating directly with your development environment, Claude Code streamlines your workflow without requiring additional servers or complex setup.
Claude Code’s key capabilities include:
- Editing files and fixing bugs across your codebase
- Answering questions about your code’s architecture and logic
- Executing and fixing tests, linting, and other commands
- Searching through git history, resolving merge conflicts, and creating commits and PRs
Research preview
Code is in beta as a research preview. We’re gathering developer feedback on AI collaboration preferences, which workflows benefit most from AI assistance, and how to improve the agent experience.
This early version will evolve based on user feedback. We plan to enhance tool execution reliability, support for long-running commands, terminal rendering, and Claude’s self-knowledge of its capabilities in the coming weeks.
Report bugs directly with the /bug
command or through our GitHub repository.
Before you begin
Check system requirements
- Operating Systems: macOS 10.15+, Ubuntu 20.04+/Debian 10+, or Windows via WSL
- Hardware: 4GB RAM minimum
- Software:
- Network: Internet connection required for authentication and AI processing
Install and authenticate
Install Claude Code
Run in your terminal: npm install -g @anthropic-ai/claude-code
Navigate to your project
cd your-project-directory
Start Claude Code
claude
to launchComplete authentication
Follow the one-time OAuth process with your Console account. You’ll need active billing at console.anthropic.com.
Core features and workflows
Claude Code operates directly in your terminal, understanding your project context and taking real actions. No need to manually add files to context - Claude will explore your codebase as needed. Claude Code uses claude-3-7-sonnet-20250219
by default.
Security and privacy by design
Your code’s security is paramount. Claude Code’s architecture ensures:
- Direct API connection: Your queries go straight to Anthropic’s API without intermediate servers
- Works where you work: Operates directly in your terminal
- Understands context: Maintains awareness of your entire project structure
- Takes action: Performs real operations like editing files and creating commits
From questions to solutions in seconds
Initialize your project
For first-time users, we recommend:
- Start Claude Code with
claude
- Try a simple command like
summarize this project
- Generate a CLAUDE.md project guide with
/init
- Ask Claude to commit the generated CLAUDE.md file to your repository
Use Claude Code for common tasks
Claude Code operates directly in your terminal, understanding your project context and taking real actions. No need to manually add files to context - Claude will explore your codebase as needed.
Understand unfamiliar code
Automate Git operations
Edit code intelligently
Test and debug your code
Encourage deeper thinking
For complex problems, explicitly ask Claude to think more deeply:
Control Claude Code with commands
CLI commands
Command | Description | Example |
---|---|---|
claude | Start interactive REPL | $ claude |
claude "query" | Start REPL with initial prompt | $ claude "explain this project" |
claude -p "query" | Run one-off query, then exit | $ claude -p "explain this function" |
cat file | claude -p "query" | Process piped content | $ cat logs.txt | claude -p "explain" |
claude config | Configure settings | $ claude config set --global theme dark |
claude update | Update to latest version | $ claude update |
claude mcp | Configure Model Context Protocol servers | $ claude mcp add pyright_lsp |
CLI flags:
--print
: Print response without interactive mode--verbose
: Enable verbose logging--dangerously-skip-permissions
: Skip permission prompts (only in Docker containers without internet)
Slash commands
Control Claude’s behavior within a session:
Command | Purpose |
---|---|
/bug | Report bugs (sends conversation to Anthropic) |
/clear | Clear conversation history |
/compact | Compact conversation to save context space |
/config | View/modify configuration |
/cost | Show token usage statistics |
/doctor | Checks the health of your Claude Code installation |
/help | Get usage help |
/init | Initialize project with CLAUDE.md guide |
/login | Switch Anthropic accounts |
/logout | Sign out from your Anthropic account |
/pr_comments | View pull request comments |
/review | Request code review |
/terminal-setup | Install Shift+Enter key binding for newlines (iTerm2 and VSCode only) |
Manage permissions and security
Claude Code uses a tiered permission system to balance power and safety:
Tool Type | Example | Approval Required | ”Yes, don’t ask again” Behavior |
---|---|---|---|
Read-only | File reads, LS, Grep | No | N/A |
Bash Commands | Shell execution | Yes | Permanently per project directory and command |
File Modification | Edit/write files | Yes | Until session end |
Tools available to Claude
Claude Code has access to a set of powerful tools that help it understand and modify your codebase:
Tool | Description | Permission Required |
---|---|---|
AgentTool | Runs a sub-agent to handle complex, multi-step tasks | No |
BashTool | Executes shell commands in your environment | Yes |
GlobTool | Finds files based on pattern matching | No |
GrepTool | Searches for patterns in file contents | No |
LSTool | Lists files and directories | No |
FileReadTool | Reads the contents of files | No |
FileEditTool | Makes targeted edits to specific files | Yes |
FileWriteTool | Creates or overwrites files | Yes |
NotebookReadTool | Reads and displays Jupyter notebook contents | No |
NotebookEditTool | Modifies Jupyter notebook cells | Yes |
Protect against prompt injection
Prompt injection is a technique where an attacker attempts to override or manipulate an AI assistant’s instructions by inserting malicious text. Claude Code includes several safeguards against these attacks:
- Permission system: Sensitive operations require explicit approval
- Context-aware analysis: Detects potentially harmful instructions by analyzing the full request
- Input sanitization: Prevents command injection by processing user inputs
- Command blocklist: Blocks risky commands that fetch arbitrary content from the web like
curl
andwget
Best practices for working with untrusted content:
- Review suggested commands before approval
- Avoid piping untrusted content directly to Claude
- Verify proposed changes to critical files
- Report suspicious behavior with
/bug
While these protections significantly reduce risk, no system is completely immune to all attacks. Always maintain good security practices when working with any AI tool.
Configure network access
Claude Code requires access to:
- api.anthropic.com
- statsig.anthropic.com
- sentry.io
Allowlist these URLs when using Claude Code in containerized environments.
Optimize your terminal setup and configure your environment
Claude Code works best when your terminal is properly configured. Follow these guidelines to optimize your experience.
Supported shells:
- Bash
- Zsh (Fish shell not currently supported)
Themes and appearance
Claude cannot control the theme of your terminal. That’s handled by your terminal application. You can match Claude Code’s theme to your terminal during onboarding or any time via the /config
command
Line breaks
You have several options for entering linebreaks into Claude Code:
- Quick escape: Type
\
followed by Enter to create a newline - Keyboard shortcut: Press Option+Enter (Meta+Enter) with proper configuration
To set up Option+Enter in your terminal:
For Mac Terminal.app:
- Open Settings → Profiles → Keyboard
- Check “Use Option as Meta Key”
For iTerm2 and VSCode terminal:
- Open Settings → Profiles → Keys
- Under General, set Left/Right Option key to “Esc+”
Tip for iTerm2 and VSCode users: Run /terminal-setup
within Claude Code to automatically configure Shift+Enter as a more intuitive alternative.
Notification setup
Never miss when Claude completes a task with proper notification configuration:
Terminal bell notifications
Enable sound alerts when tasks complete:
For macOS users: Don’t forget to enable notification permissions in System Settings → Notifications → [Your Terminal App].
iTerm 2 system notifications
For iTerm 2 alerts when tasks complete:
- Open iTerm 2 Preferences
- Navigate to Profiles → Terminal
- Enable “Silence bell” and “Send notification when idle”
- Set your preferred notification delay
Note that these notifications are specific to iTerm 2 and not available in the default macOS Terminal.
Handling large inputs
When working with extensive code or long instructions:
- Avoid direct pasting: Claude Code may struggle with very long pasted content
- Use file-based workflows: Write content to a file and ask Claude to read it
- Be aware of VS Code limitations: The VS Code terminal is particularly prone to truncating long pastes
By configuring these settings, you’ll create a smoother, more efficient workflow with Claude Code.
Manage costs effectively
Claude Code consumes tokens for each interaction. Typical usage costs range from $5-10 per developer per day, but can exceed $100 per hour during intensive use.
Track your costs
- Use
/cost
to see current session usage - Review cost summary displayed when exiting
- Check historical usage in Anthropic Console
- Set Spend limits
Reduce token usage
- Compact conversations: Use
/compact
when context gets large - Write specific queries: Avoid vague requests that trigger unnecessary scanning
- Break down complex tasks: Split large tasks into focused interactions
- Clear history between tasks: Use
/clear
to reset context
Costs can vary significantly based on:
- Size of codebase being analyzed
- Complexity of queries
- Number of files being searched or modified
- Length of conversation history
- Frequency of compacting conversations
For team deployments, we recommend starting with a small pilot group to establish usage patterns before wider rollout.
Use with third-party APIs
Connect to Amazon Bedrock
If you don’t have prompt caching enabled, also set:
Requires standard AWS SDK credentials (e.g., ~/.aws/credentials
or relevant environment variables like AWS_ACCESS_KEY_ID
, AWS_SECRET_ACCESS_KEY
). Contact Amazon Bedrock for prompt caching for reduced costs and higher rate limits.
Connect to Google Vertex AI
Claude Code on Vertex AI currently only supports the us-east5
region. Make
sure your project has quota allocated in this specific region.
Requires standard GCP credentials configured through google-auth-library. For the best experience, contact Google for heightened rate limits.
Development container reference implementation
Claude Code provides a development container configuration for teams that need consistent, secure environments. This preconfigured devcontainer setup works seamlessly with VS Code’s Remote - Containers extension and similar tools.
The container’s enhanced security measures (isolation and firewall rules) allow you to run claude --dangerously-skip-permissions
to bypass permission prompts for unattended operation. We’ve included a reference implementation that you can customize for your needs.
While the devcontainer provides substantial protections, no system is completely immune to all attacks. Always maintain good security practices and monitor Claude’s activities.
Key features
- Production-ready Node.js: Built on Node.js 20 with essential development dependencies
- Security by design: Custom firewall restricting network access to only necessary services
- Developer-friendly tools: Includes git, ZSH with productivity enhancements, fzf, and more
- Seamless VS Code integration: Pre-configured extensions and optimized settings
- Session persistence: Preserves command history and configurations between container restarts
- Works everywhere: Compatible with macOS, Windows, and Linux development environments
Getting started in 4 steps
- Install VS Code and the Remote - Containers extension
- Clone the Claude Code reference implementation repository
- Open the repository in VS Code
- When prompted, click “Reopen in Container” (or use Command Palette: Cmd+Shift+P → “Remote-Containers: Reopen in Container”)
Configuration breakdown
The devcontainer setup consists of three primary components:
- devcontainer.json: Controls container settings, extensions, and volume mounts
- Dockerfile: Defines the container image and installed tools
- init-firewall.sh: Establishes network security rules
Security features
The container implements a multi-layered security approach with its firewall configuration:
- Precise access control: Restricts outbound connections to whitelisted domains only (npm registry, GitHub, Anthropic API, etc.)
- Default-deny policy: Blocks all other external network access
- Startup verification: Validates firewall rules when the container initializes
- Isolation: Creates a secure development environment separated from your main system
Customization options
The devcontainer configuration is designed to be adaptable to your needs:
- Add or remove VS Code extensions based on your workflow
- Modify resource allocations for different hardware environments
- Adjust network access permissions
- Customize shell configurations and developer tooling
Next steps
Claude Code tutorials
Step-by-step guides for common tasks
Reference implementation
Clone our development container reference implementation.
License and data usage
Claude Code is provided as a Beta research preview under Anthropic’s Commercial Terms of Service.
How we use your data
We aim to be fully transparent about how we use your data. We may use feedback to improve our products and services, but we will not train generative models using your feedback from Claude Code. Given their potentially sensitive nature, we store user feedback transcripts for only 30 days.
Feedback transcripts
If you choose to send us feedback about Claude Code, such as transcripts of your usage, Anthropic may use that feedback to debug related issues and improve Claude Code’s functionality (e.g., to reduce the risk of similar bugs occurring in the future). We will not train generative models using this feedback.
Privacy safeguards
We have implemented several safeguards to protect your data, including limited retention periods for sensitive information, restricted access to user session data, and clear policies against using feedback for model training.
For full details, please review our Commercial Terms of Service and Privacy Policy.
License
© Anthropic PBC. All rights reserved. Use is subject to Anthropic’s Commercial Terms of Service.
Was this page helpful?