Claude Code

See also: Claude

Claude Code is an AI-powered command-line tool for agentic coding developed by Anthropic. First released as a beta research preview alongside Claude 3.7 Sonnet on February 24, 2025, and made generally available on May 22, 2025, Claude Code enables developers to delegate coding tasks to Claude directly from their terminal.

On September 29, 2025, Anthropic released Claude Code version 2.0 with significant enhancements including checkpoints for safe rollbacks, a native VS Code extension, terminal v2.0 UX improvements, and the renamed Claude Agent SDK (formerly Claude Code SDK).

Overview

Claude Code functions as an AI pair programmer that understands entire codebases and assists developers through natural language commands. The tool executes routine tasks, explains complex code, handles Git workflows, and performs multi-file edits without requiring additional servers, remote code indexing, or complex setup. It operates on the Unix philosophy, making it composable and scriptable within existing developer workflows.

The tool utilizes Claude models, with Claude Sonnet 4.5 (model ID: claude-sonnet-4-5-20250929) as the default model as of September 29, 2025. Users with Max subscriptions also have access to Claude Opus 4.1 (claude-opus-4-1-20250805) for more complex tasks. Claude Code achieved state-of-the-art performance on the SWE-bench Verified benchmark with a 77.2% score for Claude Sonnet 4.5, surpassing previous models and competitors.

As of September 2025, Claude Code generates run rate revenue of over $500 million and serves more than 300,000 business accounts, with over 5 million downloads on npm.

Popular Commands

• Claude --dangerously-skip-permissions - Run Claude Code without permission prompts (use with caution)
• claude -p "query" - Execute a programmatic query and exit
• claude update - Update to latest version
• claude mcp - Configure Model Context Protocol servers
• /rewind - Restore to previous checkpoint (v2.0+)

Popular Combinations

• Claude Code Playwright - for testing

Features

Core Capabilities

Claude Code provides comprehensive development assistance through several key features:

Feature	Description	Example Tasks
Build Features from Descriptions	Describe desired functionality in plain English; Claude creates a plan, writes code, and verifies it works	Refactors, API migrations, new feature implementation
Debug and Fix Issues	Describe bugs or paste error messages; Claude analyzes the codebase, identifies problems, and implements fixes	"Why is auth failing on refresh?"
File Management	Edit files and fix bugs across entire codebases with automatic context awareness	Multi-file refactoring
Code Analysis	Answer questions about code architecture and logic using agentic search	"Map out the payment module"
Testing & Quality	Execute and fix tests, linting, and other quality checks	"Run tests and fix failures in CI"
Version Control	Search git history, resolve merge conflicts, create commits and pull requests	"Open a PR implementing ticket #124"
Codebase Understanding	Agentic search to understand project structure without manual context selection	Automatic project exploration
Multi-file Editing	Make coordinated changes across multiple files simultaneously	Large-scale refactoring
Command Execution	Run shell commands and command line tools	"Build and start the dev server"
Checkpoints	Automatically save code state before changes with instant rollback capability (v2.0+)	Safe experimentation

Advanced Features

The tool includes several advanced capabilities that distinguish it from traditional coding assistants:

• Deep Codebase Awareness: Automatically explores and understands project structure through agentic search using tools like grep, find, and glob commands
• MCP Integration: Functions as both MCP server and client for extended tool access, supporting integrations with enterprise systems like Jira, Google Drive, Figma, and Slack
• IDE Integration: Native extensions for VS Code (generally available as of September 29, 2025) and beta extensions for JetBrains IDEs with inline edit display and real-time changes
• GitHub Integration: Can read issues, write code, run tests, submit pull requests, and automate workflows via GitHub Actions
• Background Tasks: Supports GitHub Actions integration for automated workflows and ensures uninterrupted running of development servers
• Checkpoints and Rewind: Automatically saves code states before each change, allowing rewinds via `/rewind` or double-Esc; applies to Claude's edits (not user shell commands)
• Terminal 2.0 UX: Enhanced interface with Ctrl+R for command history search, improved status displays, and more transparent development flows
• Sub Agents: Supports parallel development, such as simultaneous front-end and back-end work; delegate specialized tasks to parallel agents for complex workflows
• Hooks: Automatically trigger actions at specific points in development workflow, such as running tests after code changes or checks before submissions
• Autonomous Operation: Can maintain focus for 30+ hours on complex, multi-step tasks with Claude Sonnet 4.5, including building full production-grade applications with over 11,000 lines of code
• Context Management: Automatic context compaction and summarization to prevent context window exhaustion

Technical Specifications

System Requirements

Component	Requirement
Operating System	macOS 10.15+, Ubuntu 20.04+/Debian 10+, Windows 10+ (via WSL 1/2 or Git for Windows)
Hardware	Minimum 4GB RAM (8GB recommended for large codebases)
Software	Node.js 18+ and npm
Network	Internet connection required (authentication & model inference)
Supported Shells	Bash, Zsh, Fish
Dependencies	Git, ripgrep (recommended)
Availability	Only in Anthropic's supported countries

The tool is available only in countries and regions supported by Anthropic.

Installation

Claude Code can be installed through multiple methods:

NPM Installation (Global)

# Prerequisite: Node.js 18+
npm install -g @anthropic-ai/claude-code

# Start in your project directory
cd your-awesome-project
claude

The current stable version is 1.0.128 as of September 2025.

Native Binary Installation (Beta)

# For macOS, Linux, WSL - Stable version
curl -fsSL https://claude.ai/install.sh | bash

# Latest version
curl -fsSL https://claude.ai/install.sh | bash -s latest

# Specific version (example: 1.0.128)
curl -fsSL https://claude.ai/install.sh | bash -s 1.0.128

For Windows:

• PowerShell:

  irm https://claude.ai/install.ps1 | iex
  

• CMD:

  curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd
  

Post-installation, run `claude doctor` to verify. For Alpine Linux or musl-based systems, install additional dependencies like libgcc, libstdc++, and ripgrep.

Local Installation

After global installation, use `claude migrate-installer` to switch to local mode to avoid permission issues with auto-updates.

Authentication

Authenticate via Claude Console (default for billing), Claude App (for Pro/Max plans), or enterprise platforms like Amazon Bedrock and Google Cloud Vertex AI. Credentials are stored securely.

Usage

Command Syntax

Claude Code supports various command-line options for different use cases:

Command	Description	Example
claude	Start interactive REPL	claude
claude "query"	Start REPL with initial prompt	claude "explain this project"
claude -p "query"	Query via SDK, then exit	claude -p "explain this function"
claude -p "query"	Process piped content	claude -p "explain"
claude -c	Continue most recent conversation	claude -c
claude -c -p "query"	Continue via SDK	claude -c -p "Check for type errors"
claude -r "<session-id>" "query"	Resume session by ID	claude -r "abc123" "Finish this PR"
claude --model	Select AI model (sonnet/opus)	claude --model opus
claude --resume	Resume from recent sessions	claude --resume
claude --continue	Continue last session	claude --continue
claude update	Update to latest version	claude update
claude mcp	Configure MCP servers	See MCP docs

CLI Flags

Additional flags enhance functionality:

Flag	Description	Example
--add-dir	Add working directories	claude --add-dir ../apps ../lib
--allowedTools	Allow tools without prompt	claude --allowedTools "Bash(git log:*)" "Read"
--disallowedTools	Disallow tools	claude --disallowedTools "Edit"
--print, -p	Print response without interactive mode	claude -p "query"
--append-system-prompt	Append to system prompt (with --print)	claude --append-system-prompt "Custom instruction"
--output-format	Output format (text, json, stream-json)	claude -p --output-format json
--input-format	Input format (text, stream-json)	claude -p --input-format stream-json
--verbose	Enable verbose logging	claude --verbose
--max-turns	Limit agentic turns	claude -p --max-turns 3
--permission-mode	Set permission mode	claude --permission-mode plan
--dangerously-skip-permissions	Skip permissions (use with caution)	claude --dangerously-skip-permissions

Interactive Commands

Within the interactive REPL, users can access various slash commands:

Command	Description
/clear	Reset context window
/bug	Report issues directly to Anthropic
/config	Access configuration settings
/model	Switch between available models
/status	Check usage limits and billing
/vim	Enable Vim keybindings
/terminal-setup	Configure terminal shortcuts
/rewind	Restore to previous checkpoint (v2.0+)
/agents	Create custom subagents
/init	Generate CLAUDE.md documentation file
/compact	Summarize conversation to save context
/export	Export conversation for sharing
/statusline	Customize status line display
/install-github-app	Set up GitHub integration
/login	Switch authentication
/logout	Log out

Unix Philosophy Integration

Claude Code follows Unix philosophy principles, allowing integration with existing command-line tools:

# Process piped content
tail -f app.log | claude -p "alert me if you see repeated 5xx and suggest fixes"

# Batch annotate files
for file in *.js; do
  claude -p "Add JSDoc comments to this file:" < "$file" > "${file}.documented"
done

# Automated workflows
for f in src/**/*.ts; do
  claude -p "Add TSDoc to this file:" < "$f" > "${f%.ts}.annotated.ts"
done

Claude Agent SDK

On September 29, 2025, Anthropic renamed the Claude Code SDK to the Claude Agent SDK, reflecting its broader capabilities beyond coding. The SDK provides developers with the same infrastructure that powers Claude Code, including:

SDK Components

Component	Description
Context Management	Automatic compaction and context management
Rich Tool Ecosystem	File operations, code execution, web search, and MCP extensibility
Advanced Permissions	Fine-grained control over agent capabilities
Production Essentials	Built-in error handling, session management, and monitoring
Optimized Integration	Automatic prompt caching and performance optimizations

Example Implementation

import anyio
from claude_code_sdk import query

async def main():
    async for message in query(prompt="What is 2 + 2?"):
        print(message)

anyio.run(main)

The SDK is available for Python and TypeScript, enabling developers to build various types of agents including SRE agents, code review agents, legal assistants, and finance advisors.

Pricing and Licensing

Claude Code is available through multiple subscription tiers and deployment options:

Plan	Price (USD)	Features	Best For
Pro	$20/month ($17/mo annual)	10-40 prompts every 5 hours Sonnet 4.5 access only 40-80 hours of Sonnet 4.5 weekly	Light work on small repositories (<1,000 lines)
Max 5x Pro	$100/month	50-200 prompts every 5 hours Sonnet 4.5 and Opus 4.1 access 140-280 hours of Sonnet 4.5 weekly 15-35 hours of Opus 4.1 weekly	Regular use with medium codebases
Max 20x Pro	$200/month	200-800 prompts every 5 hours Sonnet 4.5 and Opus 4.1 access 240-480 hours of Sonnet 4.5 weekly 24-40 hours of Opus 4.1 weekly	Power users with large codebases
API	Pay-as-you-go	Standard API pricing $3/$15 per million tokens (Sonnet 4.5) No per-seat fees	Enterprise deployments and custom integrations
Team	Custom	Centralized billing Admin controls	Small to medium teams
Enterprise	Custom	SSO and SCIM Priority support	Large organizations
Education	Custom	University-wide access Discounted rates	Academic institutions

Enterprise customers can also access Claude Code through Amazon Bedrock and Google Cloud Vertex AI.

Usage Management

Claude Code implements automatic model switching to prevent users from exhausting their limits too quickly:

• Max 5x users: Automatically switches from Opus 4.1 to Sonnet 4.5 at 20% usage
• Max 20x users: Automatically switches from Opus 4.1 to Sonnet 4.5 at 50% usage

Users can override this behavior using the `/model` command.

Performance

Claude Code has demonstrated strong performance on coding benchmarks:

Benchmark	Model	Score	Notes
SWE-bench Verified	Claude Sonnet 4.5	77.2%	State-of-the-art as of September 2025; average of 10 trials, 82.0% with high-compute setup
SWE-bench Verified	Claude Opus 4	72.5%	State-of-the-art as of May 2025
SWE-bench Verified	Claude Sonnet 4	72.7%	As of May 2025
OSWorld	Claude Sonnet 4.5	61.4%	Real-world computer task benchmark
Terminal-bench	Claude Opus 4	43.2%	Terminal automation benchmark
Sustained Performance	Claude Sonnet 4.5	30+ hours	Autonomous coding, building 11K-line apps
Sustained Performance	Claude Opus 4	7 hours	Autonomous refactor validated by Rakuten
Internal Code Editing	Claude Sonnet 4.5	0% error rate	Reduced from 9% on Sonnet 4

Industry partners have reported significant improvements in development workflows:

• Cursor: Called Claude Opus 4 "state-of-the-art for coding"; Sonnet 4.5 further advances complex changes
• Replit: Reported "dramatic advancements for complex changes across multiple files"
• GitHub: Introduced Claude Sonnet 4.5 as the model powering GitHub Copilot coding agent
• Sourcegraph: Described it as "substantial leap in software development"
• Augment Code: Higher success rates in complex tasks for Sonnet 4.5
• iGent: Excellence in autonomous app development
• Manus: Improved instruction following and outputs
• Block: Boosts code quality in agents
• Cognition: Handles complex challenges better

Version History

Date	Version/Release	Description
March 2023	Initial Claude	First Claude model released
February 24, 2025	Claude 3.7 Sonnet	Released with Claude Code beta research preview
April 18, 2025	Best Practices	Published Claude Code best practices guide
May 22, 2025	Claude 4 GA	Claude Opus 4 and Sonnet 4 released; Claude Code announced as Generally Available
May 23, 2025	Cloud Integration	Extended availability to AWS Bedrock and Google Vertex AI
June 2025	IDE Extensions	VS Code and JetBrains beta extensions released
June 26, 2025	Desktop Extensions	One-click MCP server installation for browsers
June 30, 2025	Hooks Support	Claude Code hooks support added
July 4, 2025	Subagents	Custom subagents feature released
August 2025	Rate Limits	New weekly rate limits introduced for Pro and Max plans
September 29, 2025	Claude Code 2.0	Checkpoints, VS Code extension (GA), terminal v2.0, Claude Agent SDK released
September 29, 2025	Claude Sonnet 4.5	New default model with 30+ hour autonomous operation capability

Integration Capabilities

IDE Integration

Claude Code integrates with major IDEs through dedicated extensions:

• Visual Studio Code: Native extension (generally available as of September 2025) with inline edit display, dedicated sidebar panel, and real-time changes
• JetBrains: Beta extension with inline edit display, integrated via AI chat and JetBrains AI subscription

Installation is available through running Claude Code in the IDE terminal or via extension marketplaces.

Development Platform Integration

Platform	Integration Type	Capabilities
GitHub/GitLab	Full workflow	Issues, PRs, commits, code review, @claude mentions
GitHub Actions	Background tasks	Automated CI/CD workflows, official Claude Code Action
Amazon Bedrock	API Provider	Enterprise deployment
Google Vertex AI	API Provider	Enterprise deployment
GitHub Copilot	Model Integration	Claude Sonnet 4.5 available in Copilot

Model Context Protocol (MCP)

Claude Code supports the Model Context Protocol (MCP) for connecting to external tools and services. It can function as both an MCP server and client, enabling:

• Database connections
• API integrations (including Google Drive, Jira, Figma, Slack)
• Custom tool development
• External service connectivity

Best Practices

Context Management

Claude Code uses a special CLAUDE.md file for persistent context and project documentation. This file can contain:

• Project-specific instructions and conventions
• Repository etiquette and coding standards
• Developer environment setup requirements
• Custom commands and workflows
• Project architecture documentation

The file is automatically loaded when Claude Code starts in a directory and can be placed at:

• Project root (checked into version control)
• Parent directories (for monorepos)
• User home directory (~/.claude/CLAUDE.md) for global settings

Custom Commands

Users can create custom slash commands by placing Markdown files in the .claude/commands/ directory. These commands become available as reusable prompts within Claude Code sessions and can accept arguments.

Workflow Patterns

Recommended workflow patterns include:

1. Read relevant files and context first without writing code
2. Use subagents for complex problems to preserve context
3. Create a plan before implementing changes
4. Use checkpoints before major edits
5. Clear context between unrelated tasks
6. Monitor usage with `/status` command

Limitations

As of September 2025, Claude Code has several documented limitations:

• Potential for AI-generated mistakes in responses
• Tool execution reliability requires enhancement
• Limited support for very long-running commands
• Terminal rendering capability issues
• Context window can fill with irrelevant conversation during extended sessions
• Performance can degrade with accumulated irrelevant content
• OS/platform detection problems in WSL
• Potential npm permission errors
• Node.js conflicts in WSL environments
• Difficulties handling very long pasted content
• VS Code terminal truncation of long pastes
• Usage limits based on subscription; heavy users may hit caps sooner with large codebases or Opus

Known technical issues include OS detection problems in certain WSL environments and difficulties handling complex terminal UI elements.

Data Privacy

Anthropic updated its consumer privacy terms in late August–September 2025. For Claude Code when used via Free/Pro/Max consumer accounts:

• Users can choose whether chats/coding sessions are used to train models. If enabled, retention is up to 5 years; if disabled, retention is up to 30 days. (These settings apply to new or resumed chats/sessions only.)
• These consumer policies do not apply to commercial/government/education contracts or API use via providers like Amazon Bedrock and Vertex AI
• User feedback is used for improvements but not for generative model training
• Feedback transcripts are stored for only 30 days
• Limited retention periods with restricted access to session data
• Compliance with Anthropic's commercial Terms of Service
• Optional telemetry can be disabled; environment variables allow opt-out
• Local-first approach with no cloud storage of code

Reception

Claude Code has received positive reception from the developer community. As of September 2025, it has over 5 million downloads on npm. The tool has been praised for its deep codebase understanding and ability to perform complex, multi-file refactoring tasks.

Industry analysts have noted that Claude Code represents a shift from simple code completion to truly agentic development assistance. The introduction of checkpoints and autonomous operation capabilities in version 2.0 has been particularly well-received by power users who require extended coding sessions.

Community resources have emerged around Claude Code, including the awesome-claude-code repository for slash-commands and guides. A Claude Code CLI Cheatsheet has been published to help developers maximize their usage.

See also

• Claude (AI assistant)
• Anthropic
• AI pair programming
• GitHub Copilot
• Model Context Protocol
• Cursor
• Replit
• SDK
• Terminal emulator
• Command-line interface

External links

• Official Claude Code website
• Claude Code documentation
• Claude Code GitHub repository
• Claude Code on npm
• Claude Code VS Code Extension
• Claude Code community resources