Claude Code

Claude Code is Anthropic's agentic coding tool. It runs in the terminal and also in VS Code, JetBrains IDEs, Slack, the web, the desktop app for macOS, Linux and Windows, and on iOS and Android. It reads the whole codebase, proposes multi-file changes, runs shell commands, edits files and handles git workflows through natural language. On Pro, Max and Team plans a session starts in auto mode, where a separate classifier model reviews each action in place of a per-step prompt, and developers can switch to a manual mode that asks before edits, shell commands and network access. The product runs on Anthropic's own Claude models, including Fable 5.1, Opus 5.5, Sonnet 5 and Haiku 4.5. Common workflows include refactoring across many files, debugging from a natural-language description, generating test coverage, writing and running scripts, and managing git operations including commits, branches and pull requests. Background tasks, scheduled routines and parallel sessions let Claude Code work while the developer does something else. It is an MCP client and an MCP server at the same time. It connects out to external MCP servers over HTTP, SSE, stdio and WebSocket transports, and the claude mcp serve command exposes Claude Code itself as a stdio server that other applications can connect to. It works with GitHub and GitLab to read issues and open pull requests, runs in CI through GitHub Actions and GitLab CI/CD, and Apple's Xcode 26.3 integrates the Claude Agent SDK that powers it. Pricing is in USD and follows the Claude subscription tiers rather than a standalone Claude Code plan. Pro is $17 per month billed annually at $200 up front, or $20 month to month. Max 5x is $100 per month and Max 20x is $200 per month, and Anthropic notes that both are web subscription rates which may differ on mobile app stores. Team standard seats are $20 per seat per month billed annually or $25 billed monthly, Team premium seats are $100 or $125 on the same basis, and Team plans cover 2 to 150 members. Enterprise is $20 per seat per month plus usage billed at API rates, billed annually, and can be started self-serve or through sales. Pay-as-you-go API access is priced per million tokens at $10 input and $50 output for Fable 5.1, $4 and $20 for Opus 5.5, $2 and $10 for Sonnet 5, and $1 and $5 for Haiku 4.5. What the entry price does not buy is a separate allowance. Claude Code has no standalone plan and shares one usage pool with everything else on the subscription, so terminal sessions and chats draw down the same rolling five-hour and weekly limits. The Free plan does not include Claude Code, so the entry route is a paid subscription or API credentials. HIPAA coverage reaches only Enterprise and the API and depends on a Business Associate Agreement that Anthropic grants case by case after review, and Claude Team is outside that scope. Claude Code suits developers and teams who want to hand multi-step coding tasks to an agent running on Anthropic's own models, from the terminal, an IDE, Slack or a phone, on one Claude subscription. Developers who want inline suggestions inside the editor should consider GitHub Copilot or Cursor, developers who want an open-source agent that works with models from several providers should consider OpenCode, and developers who want a multi-model agent that runs on cloud machines using their own model subscriptions should consider Amp. Current state Q3 2026: the public repository has 150k stars and more than 24,000 forks, with commits landing daily, and holds plugins, the changelog and the issue tracker under a license reading All rights reserved, with use governed by Anthropic's Commercial Terms of Service. Fable 5.1 arrived on September 1, 2026 and Opus 5.5 on September 22, 2026, and both are available in Claude Code. In December 2025 Anthropic reported that Claude Code had reached $1 billion in run-rate revenue six months after public release, and announced that it was acquiring the Bun JavaScript runtime. Inputs and outputs from Anthropic's commercial products, including the API, Claude Team and Enterprise, are not used for model training by default, while consumer Pro and Max accounts carry a model training setting the user can switch off. The Claude platform holds SOC 2 Type II, ISO 27001:2022 and ISO/IEC 42001:2023, with CSA STAR and NIST 800-171 also published, and FedRAMP High is scoped to the separate Claude for Government offering.