Claude Hub
Practical guides, curated resources and best practices to master Claude Code. Community-driven and bilingual.
Guides
See allClaude Code vs GitHub Copilot: the complete 2026 comparison
Detailed Claude Code vs GitHub Copilot comparison. Features, pricing, performance, use cases: everything you need to choose between Anthropic's CLI agent and GitHub's IDE assistant.
Claude Routines: 6 Workflows I Put on Autopilot (With the Prompts)
Claude Routines run on Anthropic's servers without keeping your machine on. Complete guide with the 3 trigger types, limits, and 6 concrete prompts ready to copy.
The complete Claude guide: from beginner to power user
Everything you need to know about Claude in 2026. Web interface, Claude Code, projects, artifacts, custom instructions. The definitive English guide.
Latest posts
See allClaude Code 2.1.225 and 2.1.226: headless OAuth token bug fixed, claude agents now asks for trust
2.1.225 fixes a bug that broke headless sessions by silently swapping your long-lived OAuth token for a short-lived one, adds a workspace trust prompt to claude agents on untrusted directories, and patches several rough edges in the brand-new cross-session messaging. 2.1.226 is maintenance only. Here's what matters in these August 8 releases.
Claude Code 2.1.224: sessions can now talk to each other, a real sandbox bypass closed
2.1.224 fixes a sandbox rule that could be silently bypassed on Linux and macOS, adds cross-session messaging (SendMessage, ListAgents), and ships self-hosted runners for Team and Enterprise. Here's what matters in this August 7 release.
Claude Code 2.1.223: four permission bypasses closed, /review merges into /code-review
2.1.223 fixes four distinct ways to sneak commands past permission checks (Bash, invisible Unicode, workflow sandbox, bypassPermissions), folds /review into /code-review, and tightens 1M context window enforcement. Here's what matters in this August 6 release.
Stay up to date with Claude Hub
One email per week with the best guides and articles on Claude Code. Unsubscribe anytime.
Frequently Asked Questions about Claude Code
What is Claude Code?
Claude Code is Anthropic's command-line development tool (CLI). It lets developers code with Claude AI directly in their terminal, generating code, fixing bugs, and managing entire projects autonomously.
What is the difference between ChatGPT and Claude?
Claude is Anthropic's AI, ChatGPT is OpenAI's. For development, Claude Code stands out with its autonomous agent mode, deep code context understanding (up to 200K tokens), and native CLI integration. ChatGPT offers Codex and plugins, but with a more conversational approach.
Is Claude Code free?
Claude Code requires a Claude Pro subscription ($20/month) or Claude Max. The Anthropic API also provides access with credits. There's no unlimited free tier, but the Pro plan includes generous usage for daily development.
How to install Claude Code?
Claude Code installs via npm: npm install -g @anthropic-ai/claude-code. You need Node.js 18+ and an Anthropic account. Our installation guide covers all the steps.
What is Claude Hub?
Claude Hub is the go-to resource for mastering Claude Code. We publish practical guides, tutorials, experience reports and curated resources for developers who use Claude Code daily.
How to configure Claude Code with CLAUDE.md?
CLAUDE.md is the configuration file that gives Claude Code context about your project. Place it at your repo root with your conventions, tech stack, and specific instructions. Claude Code reads it automatically at each session.