The luongnv89/claude-howto repository provides a structured, 10-module tutorial guide for Claude Code v2.1.302 (October 2026) that teaches developers to orchestrate slash commands, persistent memory (CLAUDE.md), auto-invoked skills, specialized subagents, Model Context Protocol (MCP) servers, event-driven hooks, bundled plugins, checkpoints, and advanced features including Planning Mode, Extended Thinking, Background Tasks, and headless CI/CD execution. The guide progresses through three levels — Beginner (~2.5 hours), Intermediate (~3.5 hours), and Advanced (~5 hours) — totaling 11-13 hours, with each module building on the previous: Slash Commands (30 min), Memory (45 min), Checkpoints (45 min), CLI Basics (30 min), Skills (1 hour), Hooks (1 hour), MCP (1 hour), Subagents (1.5 hours), Advanced Features (2-3 hours), and Plugins (2 hours). It supplies production-ready, copy-paste templates for each feature — slash command Markdown files, skill directories with SKILL.md and scripts, subagent definitions, MCP JSON configs, hook shell scripts (5 hook types across 33 events in 4 categories), and plugin bundles — plus Mermaid diagrams explaining internal mechanics. Installation uses the native per-platform binary via curl, Homebrew, or WinGet (npm deprecated since v2.1.113); corporate proxies must allowlist downloads.claude.ai. The guide includes interactive self-assessment via /self-assessment and /lesson-quiz hooks, automated testing (pytest, Ruff, Bandit, mypy, EPUB generation), and supports Claude Fable 5.1, Opus 5.5, Sonnet 5.5, Haiku 5.5, and earlier 4.x/5.x models. MIT licensed, actively synced with every Claude Code release.