Claude Code: Anthropic's Agentic Coding CLI
Claude Code is Anthropic's agentic coding tool for the terminal, IDE, desktop and web. Install commands, use cases, pros and cons, and where to start.
By Claudekit Team Published 1 min read
- Type
- CLI
- Pricing
- Paid
- Repository
- github.com
- GitHub stars
- 153,195
- Website
- code.claude.com
Claude Code is Anthropic’s agentic coding tool. Unlike a chat window, it works inside your project: it reads files, runs commands, edits code, and works through multi-step tasks while you watch, steer, or step away. It is the hub that most of the other tools in this directory plug into.
What it does
- Explores and explains an unfamiliar codebase without you pasting files.
- Plans and implements features, fixes bugs, writes tests, and runs them.
- Handles git: commits, branches, merge conflicts, pull requests.
- Extends with skills, subagents, hooks, MCP servers and plugins.
Install
Native installer (recommended, auto-updates):
# macOS, Linux, WSL
curl -fsSL https://claude.ai/install.sh | bash
# Windows PowerShell
irm https://claude.ai/install.ps1 | iex
Package managers (no auto-update):
brew install --cask claude-code
winget install Anthropic.ClaudeCode
npm install -g @anthropic-ai/claude-code # requires Node.js 22+
Then run claude inside a project folder and sign in when prompted. Check the install with claude --version. Our getting started guide walks through the first session, CLAUDE.md, and the commands you will use daily.
Use cases
- Onboarding: “explain the folder structure and where requests are handled”.
- Feature work: plan in plan mode, then implement with tests as the verification loop.
- Automation:
claude -p "query"runs headless in scripts and CI; see Claude Code Action for GitHub. - Integrations: connect GitHub, databases or browsers through MCP, for example GitHub MCP Server or Playwright MCP.
Pros
- Works on real files and real commands, so it can verify its own output.
- Deep extension model (skills, subagents, hooks, MCP, plugins) shared across terminal, IDE and desktop.
- Runs in many places from one configuration.
Cons
- Requires a paid plan or API credits; heavy use consumes plan limits.
- Context management takes practice: long sessions degrade unless you
/clearand scope tasks. - It runs commands as you, so permissions and review matter.
Comparing editors? Read Claude Code vs Cursor. Want a ready-made setup on top of it? See what a Claude kit is.
Frequently asked questions
Is Claude Code free?
No. You need a paid Claude plan (Pro, Max, Team or Enterprise), a Claude Console account with API credits, or access through a supported cloud provider such as Amazon Bedrock.
Does Claude Code only run in the terminal?
No. The same agent is available as a desktop app, in VS Code and JetBrains IDEs, on the web at claude.ai/code, in Slack and in GitHub Actions.
How do I update Claude Code?
Native installs update themselves in the background. Homebrew and WinGet installs do not, so run brew upgrade claude-code or winget upgrade Anthropic.ClaudeCode periodically.