Learn Claude Code end to end — from your first session to building products on the Agent SDK. Written for developers, DevOps, cloud, SRE, and platform engineers who want to actually use it, not just watch a demo.
Sixteen modules, four phases, a two-track capstone. Every fact is verified against Anthropic's official documentation, and every module carries the date it was last checked.
Course: trainwithshubham.ai · Language: English · Format: Self-paced · Verified: 2026-08-12
| 🚀 New to Claude Code | Start at Module 1 and read in order |
| ⚡ Already installed | Skip to Module 4 — the loop and the tools |
| 🔧 Here for DevOps/SRE | Module 13 is the one written for you |
| 🔍 Looking for one thing | Topic index · Command reference |
| 📋 Want the short version | Quick reference — all 16 modules condensed |
| 🩹 Something's broken | Troubleshooting — symptom → cause → fix |
| ⚡ Already good, want sharper | Power moves — the compound techniques |
Understand what you're using, and get it running.
| # | Module | What you'll learn |
|---|---|---|
| 01 | Welcome to the Era of Agentic Coding | What an agentic loop is, the 2026 model lineup, and which Claude surface to use |
| 02 | Prompt Engineering for Agentic Work | Writing for an agent instead of a chatbot, and where instructions actually live |
| 03 | Installing Claude Code Everywhere | Install on any OS, every platform compared, authentication, and the interface |
The tools, the guardrails, and how to extend both.
| # | Module | What you'll learn |
|---|---|---|
| 04 🔬 | The Agentic Loop and Built-In Tools | Read, Write, Edit, Grep, Glob, Bash, sandboxing, and the context window |
| 05 🔬 | Permissions, Memory, and Configuration | Permission modes, auto mode, CLAUDE.md, auto memory, settings precedence |
| 06 | Planning and Executing a Real Project | Plan mode, sessions and branching, checkpoints, and monorepos |
| 07 🔬 | Skills, Commands, and Hooks | Extending Claude Code — and the one layer that's genuinely enforced |
| 08 | The Plugin Ecosystem | Installing plugins, building a marketplace, and the two security plugins |
| 09 🔬 | MCP in 2026 | Connecting external tools, tool search, and channels |
Many agents, every surface, and the boundaries an organisation sets.
| # | Module | What you'll learn |
|---|---|---|
| 10 🔬 | Subagents and Orchestration at Scale | Subagents, agent teams, dynamic workflows, worktrees, cross-session messaging |
| 11 | Claude Code Across Every Surface | VS Code, JetBrains, Desktop, web, routines, mobile, Remote Control, Slack, Chrome |
| 12 | CI/CD, Code Review, and Security | Headless mode, GitHub Actions, the review ladder, and the security story end to end |
| 13 | Infrastructure, Cloud, and Enterprise | IaC, third-party providers, self-hosted environments, gateway, admin, observability |
Build with it, then build something with it.
| # | Module | What you'll learn |
|---|---|---|
| 14 🔬 | Building Products with the Agent SDK | The SDK, the message lifecycle, and hosting agents in production |
| 15 | Capstone: Choose Your Track | Ship a full-stack feature, or build a self-healing ops agent |
| 16 | Staying Sharp: What's Next | Reading the weekly changelog and maintaining your setup |
🔬 = deep-dive module — longer, with hands-on exercises, common pitfalls, and key takeaways per chapter.
Everyone takes Modules 1–14. Module 15 splits into two tracks so a frontend developer and an SRE each leave with a portfolio piece that matches their job. Module 13 is not optional on either track — it's what makes this different from a generic AI coding tutorial.
Six ways to find something without reading a whole module:
| Topic index | A–Z concepts → the module that covers them, plus a "I want to…" table |
| Command reference | Every slash command, CLI flag, and environment variable in the course |
| Quick reference | All 16 modules condensed to bullets |
| Troubleshooting | Symptom → cause → fix. Install, login, config not loading, performance |
| Power moves | Compound techniques that combine several modules, plus the anti-patterns |
| Syllabus | Full chapter-level outline of all 16 modules |
- Read in order the first time. Modules build on each other — Module 7 makes much more sense after Module 5.
- Every module ends with links to the previous and next one, so you can read straight through.
- "Try it yourself" blocks assume a practice repo. See
labs/for what it needs to contain — or use any project of your own with a failing test in it. - Claude Code ships weekly. Each module carries a
last_verifieddate in an HTML comment at the top. Anything version-specific — model IDs, prices, flags, command names — is worth a re-check before you rely on it for something critical. Module 16 covers how.
modules/ The course. Sixteen files, one per module — this is the content
reference/ Topic index, commands, quick reference, troubleshooting, power moves, syllabus
labs/ Practice repo specification for the hands-on exercises
CLAUDE.md Instructions for Claude Code when working in this repo
Corrections are welcome, especially version drift — a command that was renamed, a flag that changed, a limit that moved. That's the most valuable kind of PR this repo can get.
Before opening one that touches module content:
- Verify against official docs. Start at
code.claude.com/docs/llms.txtfor the index andwhats-newfor recent changes. Third-party recap posts have been unreliable. - Update the
last_verifieddate in the module's HTML comment. - Keep the references in sync — a change to a module usually needs the same change in
reference/quick-reference.md, and sometimes inreference/commands.md. - Don't state what you can't verify. If a fact isn't in the official docs, cut it rather than shipping it.
See CLAUDE.md for the full content conventions.
MIT © TrainWithShubham. Use it, teach from it, adapt it — attribution appreciated.