Claude Code
✓ VerifiedAnthropic's terminal-based AI coding agent with Claude Opus 4.7, /ultrareview, Routines, /ultraplan, and 80.9% SWE-bench
Our Review
Claude Code is Anthropic's terminal-first coding experience, available in Claude desktop, web, and CLI. It now centers on the 4.6 generation (Sonnet 4.6 for broad use and Opus 4.6 for deeper reasoning tiers), with code search, multi-file edits, and permissioned command execution. The large context window and project context via CLAUDE.md make it well-suited for larger codebases.
We tested Claude Code in terminal workflows: exploring a new repo, refactoring across several files, and running tests. The permission model is clear: you approve or reject each command, and diffs are shown before applying. This feels safer than fully autonomous agents when working in production code. The experience is polished and integrated with Anthropic's broader product line.
Access is included with Claude Pro, Max, Team, and Enterprise; API usage is billed per model. If you already pay for a Claude plan and prefer a terminal-first workflow, Claude Code is a strong option. It is Anthropic-only (no third-party models), so if you need flexibility across providers, consider Aider or Continue instead.
Review updated February 25, 2026.
About
Claude Code is Anthropic's terminal-first coding agent (GA since May 2025) that lives in your terminal and handles full development workflows. As of Week 16 (April 2026, v2.1.105–v2.1.113), Claude Opus 4.7 is the default model on Max and Team Premium with a new 'xhigh' effort level (recommended for most coding work) selectable via an interactive /effort slider. Recent shipments include /ultrareview for parallel multi-agent code review in the cloud (public research preview from Week 17, v2.1.119), Routines on Claude Code on the web for templated cloud agents triggered by schedule, GitHub events, or API, /usage breakdown showing what is driving your limits, native per-platform CLI binaries replacing bundled JavaScript, /ultraplan (Week 15) for cloud plan mode from the terminal, the Monitor tool for streaming background events, /autofix-pr to enable PR auto-fix from the CLI, /team-onboarding for replayable teammate ramp-up guides, and session recap (/recap) showing what happened in unfocused terminals. Custom themes can be built from /theme or shipped via plugins. Agent Teams enable multiple Claude Code instances to collaborate on complex tasks. Integrates with VS Code and JetBrains IDEs and supports GitHub Actions for automated code review, issue resolution, and PR creation.
Key Features
- ✓Terminal-based AI agent (GA since May 2025) for full development workflows
- ✓Claude Opus 4.7 default on Max and Team Premium (Week 16, April 2026) with new 'xhigh' effort level and interactive /effort slider
- ✓80.9% SWE-bench Verified: highest autonomous coding benchmark score
- ✓/ultrareview (Week 16–17, April 2026): parallel multi-agent code review in the cloud, public research preview
- ✓Routines (Week 16, April 2026): templated cloud agents triggered by schedule, GitHub events, or API /fire endpoint
- ✓/usage breakdown (Week 16, April 2026): shows parallel sessions, subagents, cache misses, and long context driving limits
- ✓Native per-platform CLI binaries (v2.1.113): no longer invokes Node
- ✓/ultraplan (Week 15, April 2026): cloud plan mode driven from the terminal, reviewable in browser
- ✓Monitor tool (Week 15, April 2026): background watcher streams events into the conversation
- ✓/autofix-pr (Week 15, April 2026): enable PR auto-fix from the CLI for the current branch
- ✓/team-onboarding (Week 15, April 2026): generate a teammate ramp-up guide from local usage
- ✓Session recap (/recap, Week 17): one-line summary of what happened while a terminal was unfocused
- ✓Custom themes (v2.1.118): build from /theme, hand-edit JSON, or ship in plugins
- ✓Self-pacing /loop schedules its own ticks based on the task
- ✓Agent Teams: multiple Claude Code instances collaborate on complex tasks
- ✓Plan and execute multi-file edits, run tests, debug errors, manage git
- ✓CLAUDE.md file for project-specific context and instructions
- ✓VS Code extension and JetBrains plugin for IDE integration
- ✓GitHub Actions: automated code review, issue resolution, and PR creation
- ✓30+ hour task endurance for long-running development sessions
- ✓Permissioned command execution with confirmation prompts
- ✓Context compaction for handling long conversations efficiently
- ✓MCP support for connecting to external tools and data sources
Pros & Cons
Pros
- Supports multiple platforms (macOS, Linux, Windows)
- Broad integrations (9+ connectors)
- SSO available for enterprise
Cons
- No free tier; paid plans only
- No BYOK; model choice dictated by vendor
Use Cases
- →Autonomous multi-file refactoring and codebase modernization
- →Agent Teams collaborating on complex development tasks
- →Writing comprehensive test suites with automatic iteration
- →Debugging complex issues with full codebase context
- →Automated code review and PR creation via GitHub Actions
- →Long-running development sessions (30+ hour endurance)
- →Git workflow management and automated commits
Technical Details
Languages
AI Models
Integrations
Get Claude Code Updates
Be the first to know when Claude Code changes pricing, adds features, or offers deals.
No spam, unsubscribe anytime.
Frequently Asked Questions
What is Claude Code?
Claude Code is Anthropic's terminal-first coding agent (GA since May 2025) that lives in your terminal and handles full development workflows. As of Week 16 (April 2026, v2.1.105–v2.1.113), Claude Opus 4.7 is the default model on Max and Team Premium with a new 'xhigh' effort level (recommended for most coding work) selectable via an interactive /effort slider. Recent shipments include /ultrareview for parallel multi-agent code review in the cloud (public research preview from Week 17, v2.1.119), Routines on Claude Code on the web for templated cloud agents triggered by schedule, GitHub events, or API, /usage breakdown showing what is driving your limits, native per-platform CLI binaries replacing bundled JavaScript, /ultraplan (Week 15) for cloud plan mode from the terminal, the Monitor tool for streaming background events, /autofix-pr to enable PR auto-fix from the CLI, /team-onboarding for replayable teammate ramp-up guides, and session recap (/recap) showing what happened in unfocused terminals. Custom themes can be built from /theme or shipped via plugins. Agent Teams enable multiple Claude Code instances to collaborate on complex tasks. Integrates with VS Code and JetBrains IDEs and supports GitHub Actions for automated code review, issue resolution, and PR creation.
How much does Claude Code cost?
Claude Code offers subscription pricing. Plans include: Claude Pro: $20/month, Claude Max 5x: $100/month, Claude Max 20x: $200/month, Teams: $25-$150/seat/month, API Usage: Opus 4.6: $5/$25 MTok | Sonnet 4.6: $3/$15 MTok.
What programming languages does Claude Code support?
Claude Code supports 1+ programming languages including Any language via local files and repositories.
What AI models does Claude Code use?
Claude Code is powered by claude-opus-4-7, claude-opus-4-6, claude-sonnet-4-6.
What platforms does Claude Code support?
Claude Code is available on macOS, Linux, Windows.
What can Claude Code do?
Claude Code provides code completion, code generation, debugging, AI chat, agentic/autonomous mode. Key features include: Terminal-based AI agent (GA since May 2025) for full development workflows, Claude Opus 4.7 default on Max and Team Premium (Week 16, April 2026) with new 'xhigh' effort level and interactive /effort slider, 80.9% SWE-bench Verified: highest autonomous coding benchmark score.
Related Articles
Claude Opus 4.8: model upgrade plus effort control and Claude Code dynamic workflows
Anthropic released Claude Opus 4.8 with improved performance and launched new features including effort control on claude.ai and dynamic workflows in Claude Code.
Claude Code 2.1.142: new claude agents flags + fast mode defaults to Opus 4.7
Claude Code 2.1.142 adds new claude agents flags for background sessions, switches fast mode to Opus 4.7 by default, and ships a large set of reliability fixes across plugins, MCP, daemon behavior, and OS-specific edge cases.
Anthropic (May 2026): higher Claude Code limits + increased Claude Opus API rate limits
Anthropic says it doubled Claude Code’s five-hour rate limits for paid plans, removed peak-hours reductions for some users, and significantly raised Claude Opus API rate limits.
Workflow Resources
Cookbook
AI-Powered Code Review & Quality
Automate code review and enforce quality standards using AI-powered tools and agentic workflows.
Cookbook
Building AI-Powered Applications
Build applications powered by LLMs, RAG, and AI agents using Claude Code, Cursor, and modern AI frameworks.
MCP Server
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
MCP Server
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
Pricing and features change frequently—confirm on the vendor site.
We may earn a commission if you sign up. See our disclosure.
Pricing
Claude Pro
$20/month
- Claude Code access in terminal and desktop
- All models including Sonnet 4.6 and Opus 4.6
- Higher usage limits than Free tier
Claude Max 5x
$100/month
- 5x Pro usage for Claude Code
- Extended thinking mode
- Agent Teams support
Claude Max 20x
$200/month
- 20x Pro usage for Claude Code
- Maximum capacity for heavy agent workflows
- Priority routing
Teams
$25-$150/seat/month
- Claude Code for team development
- Collaboration and admin controls
- Shared project context
API Usage
Opus 4.6: $5/$25 MTok | Sonnet 4.6: $3/$15 MTok
- Direct API access to Claude Code capabilities
- Prompt caching and batch processing discounts
- GitHub Actions integration for CI/CD
Company
- Name
- Anthropic
- Founded
- 2021
- Location
- San Francisco, CA
Links
Similar Tools
Compare Claude Code with these alternatives
Claude Code
Subscription