Claude CodeAnleitung
How to check your Claude usage: web, app and Claude Code
Settings > Usage on claude.ai and Desktop, /usage in Claude Code, a gauge on the page: what each view shows, what it misses, and where resets appear.
Claude Code
Claude Code nutzt dieselben Limits wie claude.ai: Die Fünf-Stunden-Session und das Wochenlimit teilen sich Terminal, IDE, Apps und Web. Zusätzlich kann es ein eigenes Limit für eine Modellfamilie wie Opus oder Sonnet melden — mit /model auf ein anderes Modell zu wechseln, lässt Sie weiterarbeiten. Diese Artikel zeigen, was das Terminal Ihnen mit /usage, /cost und /stats sagt, und was nicht: was Ihr Browser im selben Fenster verbraucht hat oder alles, was älter ist als die lokalen Transkripte, die es aufbewahrt. Dazu kommen Einrichtungsanleitungen für MCP-Server, Hooks und Plugins sowie Gewohnheiten, mit denen eine lange Session länger hält.
Alle Artikel
Claude CodeAnleitung
Where do your Claude Code tokens go?
Run /usage in Claude Code to see skills, subagents, plugins and MCP servers for this machine. Why usage climbs, and how to see it across every PC.
Claude CodeAnleitung
Claude Code Hooks: Automate Your Dev Workflow
Master Claude Code hooks to enforce linting, block secrets, and automate every repetitive task in your development workflow.
ModelleAnleitung
Which Claude AI Model Should You Use? Mid-2026 Guide
Sonnet 5, Opus 4.8, Haiku 4.5, or Fable 5? A practical decision framework for choosing the right Claude AI model for your workload in mid-2026.
News
Claude AI Privacy Policy July 2026: What Changed
Anthropic's updated Claude AI privacy policy took effect July 8, 2026. Here's what changed with law enforcement sharing, agentic data handling, and what users should do.
Anleitungen
Context Engineering with Claude AI: Why Prompts Alone Aren't Enough
Context engineering is replacing prompt engineering as the key skill for building powerful Claude AI agents. Learn what changed and how to apply it.
News
Anthropic Opens Seoul Office: Claude Lands at Samsung, LG, and NAVER
Anthropic opened its Seoul office and announced major Claude AI deployments across Samsung, LG, NAVER, and the Korean government.
Claude CodeNews
Anthropic Accuses Alibaba of Massive Claude AI Distillation Attack
Anthropic says Alibaba used 25,000 fake accounts to extract Claude AI capabilities in the largest known distillation attack. Here's what happened and what it means.
Claude CodeNews
Claude Programmed a Robot Dog 20x Faster Than Humans
Anthropic's Project Fetch Phase Two shows Claude Opus 4.7 completing robotics tasks 20x faster than human teams — without any human help.
Claude CodeNews
Anthropic's "When AI Builds Itself" Report Explained
Anthropic reveals Claude writes 80% of its own code and calls for a global AI pause option. Here's what their landmark report means.
Claude CodeAnleitung
Claude AI Enterprise MCP Auth: Zero-Touch Setup With Okta
Anthropic launched Enterprise-Managed Authorization for Claude MCP connectors, enabling zero-touch provisioning through Okta for Team and Enterprise plans.
Anleitungen
Claude Code Dynamic Workflows: Run Hundreds of AI Agents in Parallel
Dynamic workflows let Claude Code orchestrate hundreds of parallel subagents to tackle massive engineering tasks. Here's how they work and when to use them.