Skip to main content
📖 The AI Tool Bible
Claude Code preview image
Claude Code logo

Claude Code

Not yet source-checked

Anthropic's agentic coding tool that reads, edits, and ships code from the terminal, IDE, or web.

Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked Pricing captured How we rate

Freemium· Free tier · from $20/moCodingClaude (Opus / Sonnet / Haiku)8.2 / 10

In short

Claude Code is a first-party agentic coding agent that executes multi-file edits, runs shell commands, and manages GitHub/GitLab issues. It is best for developers who prefer terminal-based automation and are already subscribed to Anthropic's Pro or Max plans.

Best for

Pick Claude Code if you live in a terminal, want a true agent (not just autocomplete), and are already paying for Anthropic.

Skip if

Skip it if you need an open-source agent, offline operation, or a cheap pay-per-token CLI without a subscription.

Claude Code is Anthropic's first-party coding agent, built around the Claude model family (currently Opus 4.7 as the default driver). It maps codebases, performs multi-file edits, runs shell commands, drives a browser, and ties into GitHub/GitLab for full issue-to-PR loops. You can drive it from a terminal, the VS Code or JetBrains extensions, the desktop app, claude.ai/code in a browser, or even Slack, and a 'Routines' feature lets you schedule recurring agent runs.

It is the most direct competitor to Cursor, Cline, and OpenAI Codex CLI, and unlike Cursor it is a true CLI-first agent rather than an editor fork. Access is bundled with Anthropic's consumer plans: Pro at $17-20/mo, Max 5x at $100/mo, Max 20x at $200/mo, plus pay-as-you-go via the Anthropic API for Console accounts. For shops already paying for Claude, it is effectively free; for everyone else the Max tiers are the realistic plan once you actually use it for serious refactors.

It supports MCP servers for custom tools, has hooks for automating behaviour on events, and runs the same model you can call from the API, so prompts and skills are portable. The honest caveat: it is closed-source, token-greedy on large repos, and Opus pricing eats Max quotas fast on long agentic runs.

Editor's take

Claude Code is the agent we reach for first when a job needs a real plan-execute-verify loop rather than tab-complete. The Max 5x plan is the sweet spot; below that, Opus runs will throttle you mid-refactor. Cursor is still nicer for tight inner-loop edits, but for autonomous work Claude Code is ahead.

— The AI Tool Bible editorial team

Pros

  • ✅ True agentic CLI plus first-party VS Code and JetBrains extensions
  • ✅ Native GitHub/GitLab issue-to-PR loop with computer-use fallback
  • ✅ MCP, hooks, and Routines make automation and scheduling first-class
  • ✅ Same Claude model as the API, so prompts and skills port cleanly
  • ✅ Bundled into existing Pro/Max plans rather than a separate SKU

Cons

  • ⚠️ Closed source; you are locked to Anthropic's model and billing
  • ⚠️ Opus runs burn Max quotas fast on large agent loops
  • ⚠️ Windows terminal experience still lags macOS/Linux
  • ⚠️ No offline or self-host story for regulated environments

Pricing (captured )

TierMonthlyAnnualPer seatKey features
Free$0——
  • Limited usage every 5 hours and every week
  • Chat on web, desktop, and mobile
  • Search the web, create files, and run code
  • Memory across conversations
Pro$20$17—
  • Fable, paid with usage credits
  • Hand off and schedule tasks
  • Claude Data, plus Sheets and Whiteboards (beta)
  • Claude Code
Max$100——
  • 5x Pro usage every 5 hours and every week
  • Fable included, up to half your weekly limit
  • $100 a month in API credits to build on the Claude Platform
  • Early access to advanced Claude features
Ultra$200——
  • No 5-hour limit
  • 10x Pro usage every week
  • $200 a month in API credits, up from $100 on Max
Enterprise—US$20/seat/monthYes
  • Admins set user and org spend limits
  • Role-based access with fine grained permissioning
  • System for Cross-domain Identity Management (SCIM)
  • Audit logs

Prices change; we show the grid as captured on Nov 14, 2026. Check current pricing on the vendor's site →

Facts

Platforms
macos, linux, cli, vscode-extension, jetbrains-plugin, api
API available
Yes
Free trial
Yes
Company
Anthropic, Inc.
Parent company
Anthropic
Launched
Jan 1, 2021
Model used
Claude (Opus / Sonnet / Haiku)
Vendor pages
Changelog
Hacker News
195 stories · top 1,298 points · last Nov 5, 2026 · checked Nov 9, 2026

Where this tool sits

Use cases

agentic-codingcodebase-refactorissue-to-prterminal-automationide-assistant

Recent updates from Anthropic, Inc.

Frequently asked

How much does Claude Code cost?
Access is bundled with Anthropic's consumer plans, including Pro at $20/month and Max tiers at $100 or $200/month. A free tier is also available, and pay-as-you-go options exist via the Anthropic API.
Where can I use Claude Code?
You can drive it from a terminal, VS Code or JetBrains extensions, a desktop app, the claude.ai/code browser interface, or Slack. It also supports scheduling recurring runs through its Routines feature.
Does Claude Code support GitHub and GitLab?
Yes, it ties into GitHub and GitLab to handle full issue-to-PR loops. It also supports MCP servers for custom tools and hooks for automating behavior on specific events.
Is Claude Code open source?
No, Claude Code is closed-source. It is locked to Anthropic's model family and billing system, with no offline or self-hosted option for regulated environments.

Compare Claude Code with similar tools

All alternatives →

Explore related

Reviews