Claude Code

CodeDesktopWebGuidesMCPsSkillsToolsExtensions

Orchestrate teams of Claude Code sessions working together. Shared tasks, inter-agent messaging, and centralized management for parallel AI development.

Claude Opus 4.6 leads Terminal-Bench 2.0, Humanity's Last Exam, and GDPval-AA. Better coding, 1M context beta, 128K output, and same $5/$25 pricing.

Compare every Claude model Anthropic has released. Specs, pricing, benchmarks, and practical guidance from Claude 3 through Opus 4.6.

Claude Code Session Memory auto-recalls past work and writes summaries in the background. Learn how it works and where files live.

Pair builder and validator agents using the Claude Code task system. Build-then-validate workflows with dependency chains.

Set up Claude Code sandboxing for filesystem and network isolation. Covers macOS Seatbelt, Linux bubblewrap, and security config.

Complete reference for Claude Code settings.json, environment variables, and the 5-scope hierarchy. Every setting key documented.

Configure your terminal for Claude Code. Set up Shift+Enter line breaks, vim mode, notifications, and tips for VS Code and iTerm2.

Build Claude Code agents that validate their own output using PostToolUse hooks, Stop hooks, and read-only validator agents.

Configure custom keyboard shortcuts in Claude Code. Reference for all 17 contexts, keystroke syntax, and keybindings.json examples.

Set up a custom Claude Code status line showing model name, git branch, cost, and context usage. Includes ready-to-copy scripts.

Use --init with slash commands to load different context per session type. A simpler alternative to setup hooks for context loading.

Setup hooks combine deterministic scripts with agentic oversight. Automate installation, maintenance, and CI/CD with Claude Code.

Claude Code reduced its autocompact buffer from 45K to 33K tokens. Learn what changed, what triggers autocompact, and workarounds.

Proactively backup your Claude Code session before compaction hits. StatusLine monitoring and threshold triggers keep your work safe.

SessionStart, SessionEnd, Setup, and PreCompact hooks for Claude Code. Auto-load context at startup and clean up on session end automatically.

Use the Stop Hook to ensure Claude finishes tasks before responding. Run tests automatically, validate output, and prevent incomplete work.

The community built Ralph Wiggum. Anthropic built native task management. Multi-session coordination with dependencies and blockers built in.

One command to install Claude Code on Windows, Mac, or Linux. No Node.js, no npm, no PATH configuration. Automatic updates included.

Set up Context7 MCP server for Claude Code. Access up-to-date library documentation directly in your AI coding sessions with one config.

Set up MCP servers in Cursor IDE. Step-by-step guide to configure Cursor MCP servers for AI-powered development with Model Context Protocol.

Configure enable_tool_search for Claude Code MCP lazy loading. Reduce context usage by 95% with MCP Tool Search and optimize your context window.

Combine Ralph Wiggum loops with thread-based engineering for autonomous Claude Code development that ships production features while you sleep.

The complete guide to Ralph Wiggum loops. Learn stop hooks, completion promises, and verification-first workflows that ship features overnight.