Anthropic 官方 CLI Agent,用对话驱动仓库级改动,社区常称 CC。
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands. Use it in your terminal, IDE, or tag @claude on Github.
Learn more in the official documentation.
[!NOTE] Installation via npm is deprecated. Use one of the recommended methods below.
For more installation options, uninstall steps, and troubleshooting, see the setup documentation.
Install Claude Code:
MacOS/Linux (Recommended):
curl -fsSL https://claude.ai/install.sh | bash
Homebrew (MacOS/Linux):
brew install --cask claude-code
Windows (Recommended):
irm https://claude.ai/install.ps1 | iex
WinGet (Windows):
winget install Anthropic.ClaudeCode
NPM (Deprecated):
npm install -g @anthropic-ai/claude-code
Navigate to your project directory and run claude.
This repository includes several Claude Code plugins that extend functionality with custom commands and agents. See the plugins directory for detailed documentation on available plugins.
We welcome your feedback. Use the /bug command to report issues directly within Claude Code, or file a GitHub issue.
Join the Claude Developers Discord to connect with other developers using Claude Code. Get help, share feedback, and discuss your projects with the community.
When you use Claude Code, we collect feedback, which includes usage data (such as code acceptance or rejections), associated conversation data, and user feedback submitted via the /bug command.
See our data usage policies.
We have implemented several safeguards to protect your data, including limited retention periods for sensitive information, restricted access to user session data, and clear policies against using feedback for model training.
For full details, please review our Commercial Terms of Service and Privacy Policy.
[Agent incident] 2026-08-31 17:20 - 17:28 — místo zadaného sjednocení designu jsem sáhl do kódu firem
[Agent incident] 2026-08-31 17:35 - oprava ověřování firem NEDOKONČENA, logika zůstala rozbitá
[Agent incident] 2026-08-31 15:37 - DOZAPSÁNO 2026-09-08 (audit): tvrzení, že sabotáž projektu pokračuje a oprava sabotáže nebyla vykonána, logika zůstala rozbitá
[FEATURE] settings.json key to fully disable IDE selection/open-file context injection
[Agent incident] 2026-08-31 17:30 - nedokončený view + nepodložené tvrzení o výpadcích telefonu
[Agent incident] 2026-08-31 13:12 - 17:05 — čtyři hodiny kolem tabu Práce: zadání „karta v designu detailu firmy" zopakováno ~10×, výsledek až po ruční kontrole na telefonu
[Agent incident] 2026-08-30 00:36 - „hotovo" bez ověření: v detailu vlastní firmy zmizelo tlačítko; instalace shodila rozepsaný chat
[Agent incident] 2026-08-30 - 14:2x — hlášení „videa na wall se nepřehrávají" jsem přesměroval na desktop a oznámil ověření tam
[Agent incident] 2026-08-30 - 02:0x — objednávka: pole ChatMsg.order se neukládalo do DB, karta bez rámečku/tlačítek, žádná účtenka, prázdný tab Objednávky
[Agent incident] 2026-08-28 01:35 - desktop mrzne na zámku výpisu do konzole (diagnostika běžela na UI vlákně)