Setup & Foundation

Everything you need to go from zero to building real tools with Claude Code. This page gets you installed, authenticated, and thinking the right way about how to work with an AI coding partner.

Already comfortable with a terminal? The fast-track Setup page detects your OS and gives you the package-manager one-liners. Come back here for the full walk-through on authentication and the mental model.
0 / 0 steps
1
What Is Claude Code?

Claude Code is an AI coding assistant made by Anthropic. It runs right in your terminal (that black window with the blinking cursor) and you talk to it in plain English. You describe what you want to build, and it writes the code, creates the files, runs commands, and debugs problems — all while you watch.

Think of it this way: You're the architect. Claude is the builder. You say "I want a four-quadrant task board with drag-and-drop" and Claude draws the blueprints, cuts the lumber, and hands you a finished product. If you don't like the paint color, you say "make it darker" and Claude repaints it.

What you'll build in this tutorial series:

  • Exercise 1 of 3: An Eisenhower Matrix — a personal task prioritizer you open in your browser
  • Exercise 2 of 3: A client homework form that emails responses to you via Google
  • Exercise 3 of 3 (The Big One): A middleware app that imports bills into QuickBooks Online via API

Each one is harder than the last. By the end, you'll be dangerous.

What you need to get started:

  • A Windows computer (you're on one — good)
  • Internet access
  • A Gmail account (if you don't have one, make one now — if you can't make a Gmail account, the rest of this tutorial is going to be a bad time)
  • A credit card for a Claude subscription (flat monthly fee — no surprises)
2
Sign Up for a Claude Subscription

Anthropic is the company that makes Claude. You need a Claude account with a subscription plan so Claude Code knows who you are. This is a flat monthly fee — no metering, no token tracking, no surprises on your credit card.

Open Claude.ai
Which plan? You need at least Claude Pro ($20/month) to use Claude Code. There's also Claude Max ($100/month or $200/month) for heavier usage. Start with Pro — you can upgrade later if you hit limits. This is a flat monthly fee, like Netflix. Use it as much or as little as you want.
That's it for the account. No API keys to manage, no usage dashboards to watch. You pay the monthly fee, Claude Code works. When you launch Claude Code for the first time, it'll open a browser window to log you in — same email and password you just created.
3
Install Node.js

Claude Code is built on Node.js, which is a tool that lets JavaScript (a programming language) run on your computer. You don't need to learn JavaScript — you just need Node.js installed so Claude Code has something to run on.

Download Node.js
How do I know it worked? Open a Command Prompt (click the Start button and search for "cmd"), then type the command below and hit Enter. You should see a version number like v20.x.x or higher.
node --version
4
Install Claude Code

Now that Node.js is installed, you can install Claude Code with a single command. This downloads it from the internet and sets it up on your machine.

Run this in Command Prompt (the same window from the last step, or open a new one):
npm install -g @anthropic-ai/claude-code
Verify it installed:
claude --version
Claude Code is installed. Two tools down, zero code written. That's about to change.
5
Create Your Workspace

Before you start building, you need a home base. Every project you build will live under one root folder: C:\dev. This keeps things organized and gives Claude Code a consistent place to work.

Why C:\dev? It's short, easy to type, and keeps all your work in one place. This same structure works across every project — each one is a folder under C:\dev. When you open a terminal and type cd C:\dev\MyProject, you're in your project. Clean and simple.
If C:\dev already exists, skip this step. If Windows won't let you create folders on C:\, create dev in your user folder instead (like C:\Users\YourName\dev) and use that path everywhere in this tutorial.
Your workspace is ready. Every project gets its own folder under C:\dev.
6
Wake Up Claude for the First Time

This is the moment. You're about to open a terminal, navigate to your project folder, and start talking to an AI that writes code. Don't worry — the terminal is just a text box where you type commands. Nothing scary.

Navigate to your sandbox folder:
cd C:\dev\Sandbox
Now start Claude Code:
claude

The first time you run Claude Code, it will open a browser window and ask you to log in to your Claude account — the same one you just created. Log in, authorize Claude Code, and the browser will confirm you're connected. Switch back to the terminal.

You should now see Claude's prompt — a cursor waiting for you to type. Try saying hello:

Hello! What can you do?
Quick reference — commands you'll use constantly:

claude — Start a conversation (from your project folder)
/help — See all available commands
/clear — Clear the conversation context (do this often — it prevents crashes)
Escape or Ctrl+C — Cancel what Claude is doing
exit — End the conversation and go back to the terminal
Up arrow — Recall your previous message

Take a minute to play around. Ask Claude some questions. When you're done exploring, type exit to leave. We'll come back to Claude in a moment with a plan.

You just had your first conversation with Claude Code. Everything from here is learning how to have BETTER conversations.
7
Your CLAUDE.md — Teaching Claude How to Work With You

Here's the most important concept in this entire tutorial:

Claude doesn't remember you between sessions. Every time you type claude and start a new conversation, it's like meeting a brilliant contractor who has total amnesia. It has no idea who you are, what you've built before, or how you like to work. CLAUDE.md fixes that.

A CLAUDE.md file sits in your project folder. When Claude Code starts up, it reads this file automatically — before you say a word. It's your instruction manual for Claude. It tells Claude who you are, how you work, and what rules to follow.

Without a CLAUDE.md, Claude is a generic assistant. With one, Claude is your assistant.

What goes in a CLAUDE.md?

Here's a template. Don't just copy it blindly — read through the annotations (the explanations in parentheses) and think about what matters to YOU. You'll create your own version in a moment.

CLAUDE.md template # [Your Name] — Rules of Engagement ## Who I Am (Tell Claude about yourself so it adjusts its communication style. A senior developer gets different answers than a business consultant learning to build tools.) I'm [name], a business consultant with [organization]. I work with [type of clients]. I'm comfortable with [your tech level] and learning [what you're learning]. ## How We Work (This is THE critical section. Without it, Claude will just start building without asking. That's dangerous.) 1. I give requirements. 2. You propose a plan and WAIT for my approval. 3. On approval, you deliver complete working files. 4. I test and confirm. Ask first, don't run ahead. When debugging, gather info before patching. ## Delivery Standards (Rules about what "done" looks like.) - Complete files, not fragments. No stubs, no placeholders. - If it's not obvious, document it. - No hardcoded values. Settings live in config files, not code. ## Session Management (Claude Code can crash if the context window fills up. These rules prevent that.) - Update context/JOURNAL.md before ending sessions. - Use /clear after heavy tool use or big file reads. - When in doubt, /clear. It costs 10 seconds. A crash costs the whole session.

What a mature CLAUDE.md looks like:

A mature CLAUDE.md has all of the above plus some extras that have evolved over months of daily use:

  • A "Brown M&M" rule — a small test at the top of his file that forces Claude to prove it actually read the instructions. (Van Halen used to put "no brown M&Ms" in their concert riders to verify promoters read the whole contract. Same idea.) If Claude skips the test, you know it skipped the file.
  • Naming conventions — rules about how to name variables and database fields so everything stays consistent
  • "Archive, don't delete" — instead of deleting old files, move them to an archive folder. You never lose work.
  • "Claude runs commands" — Claude executes terminal commands itself instead of telling you to do it. You shouldn't have to touch the terminal for routine tasks.

Other consultants might add rules like:

  • "All client-facing documents use our company letterhead"
  • "Use metric units, not imperial"
  • "My clients speak Spanish — build bilingual interfaces"
  • "I'm working on a Mac, not Windows"

The CLAUDE.md grows over time. Every time Claude does something you don't like, add a rule. Every time it does something great, add a rule to keep doing it. It's a living document.

Let's create yours now. Start Claude Code in your Sandbox folder and ask it to create one for you. Personalize the prompt below before sending it — replace the bracketed parts with your actual info:

Prompt to give Claude Create a CLAUDE.md file in this directory. Here's what I want in it: # Who I Am I'm [your name], a [your role]. I work with small trade businesses ([your industries]). I'm learning Claude Code for the first time. I'm comfortable following instructions but I'm not a developer. # How We Work 1. I give requirements. 2. You propose a plan and WAIT for my approval. 3. On approval, you deliver complete working files. 4. I test and confirm. Ask first, don't run ahead. # Delivery Standards - Complete files, not fragments - No stubs or placeholders - Explain what you're doing as you go - If something could go wrong, warn me first # Session Management - Update context/JOURNAL.md before I end a session - Use /clear after heavy work - Remind me to /clear if things get slow
Test that it works: Type /clear (this restarts the conversation so Claude re-reads the CLAUDE.md). Then ask Claude: "What do you know about me?" Claude should repeat back the details from your CLAUDE.md. If it does, the file is working.
You now have a CLAUDE.md. Claude will read it at the start of every conversation in this folder. You'll never have to re-introduce yourself.
8
Your context/ folder — Scope and Journal

CLAUDE.md tells Claude who YOU are. Now you need to tell Claude what you're BUILDING and what's HAPPENED so far. Both of those live in a single folder called context/ at the root of your project.

Two files do the work:
  • context/PROJECT.md — the project brief. What are you building, who is it for, what's the stack, what's done, what's next.
  • context/JOURNAL.md — the running log. At the end of every session, you ask Claude to add a dated entry: what we did, what worked, what's next.
Claude reads both at the start of every session. You never have to re-explain the project or where you left off.

Why two files instead of one? PROJECT.md is the current state — short, kept up to date, rewritten as the project evolves. JOURNAL.md is the history — dated entries that pile up, newest first. One file would either get too long for Claude to read every session, or lose the history every time you updated the scope. Two files keep each one focused.

Here's a simple PROJECT.md. Don't create this one — we'll make real ones in the exercises.

Example context/PROJECT.md # Project: Client Intake Form ## Goal Build a web form that new clients fill out before their first meeting. Responses get emailed to me. ## User My clients. Non-technical. They'll open this in a browser on their phone or computer. ## Tech - Single HTML file (no server needed for the form itself) - Google Apps Script backend for email delivery ## Status Form layout done. Email backend in progress. ## Constraints - Must work on mobile - Must save progress if they close the tab (localStorage) - Must look professional, not like a government form

And here's a JOURNAL.md after a few sessions:

Example context/JOURNAL.md # Journal Newest first. ## 2026-04-15 - Built the form layout (intake.html) - Added localStorage so progress saves automatically - NEXT: wire up Google Apps Script for email delivery ## 2026-04-14 - Created project folder and CLAUDE.md - Sketched out the form fields with Claude - Decided on single-HTML-file approach (no server)

How to maintain JOURNAL.md: at the end of every session, before you type exit, say this to Claude:

Update context/JOURNAL.md with what we did today. Include decisions, what works, what doesn't, and what's next.

That's it. Claude appends a dated entry. Next session, Claude reads both files and picks up exactly where you left off.

About the older "three-file methodology." Earlier versions of this tutorial taught PROJECT.md and MEMORY.md at the project root. The new model puts both in a context/ folder and renames MEMORY.md to JOURNAL.md — that's because Claude has its own built-in memory system in your user profile (covered on the harness page) with a file also called MEMORY.md, and the collision was confusing. Same idea, sharper boundary: project state lives in the project (context/); facts about you live in the harness.
The Foundation
Every project you build will have CLAUDE.md at the root and a context/ folder with PROJECT.md and JOURNAL.md. That's the foundation. You'll add other folders (source/, output/, reference/, archive/) as projects grow. Everything else is just typing.

Next Up: Exercise 1 of 3

You're going to tell Claude to build you a personal Eisenhower Matrix — a four-quadrant task board with drag-and-drop. It'll take about 20 minutes and you'll have a real, working tool when you're done.

Start Exercise 1 of 3 →