Setup & Foundation

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.

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 pushes data into a business system via API. This one comes in two versions and you only do one of them — take the QuickBooks version if your books are in QuickBooks Online, or the Contractors Cloud version if your jobs live in that CRM.
• Then, page 5 — Harness & Memory: the settings, memory files, and habits that make every project after this one go faster

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 at accounts.google.com/signup (free)
• A credit card for a Claude subscription (flat monthly fee — no surprises)

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.

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.

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.

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.

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.

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:

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.

Git is your undo button and a free offsite backup. Set it up once — from here on, you just tell Claude to handle the Git work.

Now let Claude do the rest. From your project folder, start claude again — just like the last section — and say:

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

A CLAUDE.md is a plain text file Claude Code reads automatically when it starts — before you say a word. It's your instruction manual for Claude, and it comes in two levels. The global one lives in your user profile (C:\Users\[you]\.claude\CLAUDE.md) and applies to every project on your machine — who you are and how you work belongs there, written once. A project CLAUDE.md sits at a project's root and adds rules for that one project only ("this app is a single HTML file, no server") — you'll create your first of those in Exercise 1. Right now, we're making the global one.

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

What goes in a CLAUDE.md?

Write this one in your own words. CLAUDE.md is how Claude learns who you actually are, so a file copied from somebody else quietly teaches Claude to expect somebody else — that's worse than having no file at all. The builder below asks you a few plain questions and assembles the file out of your answers. Nothing is filled in for you; the grey text inside each box is only an example of the kind of answer, and it disappears the moment you start typing.

# Marisol — How I Work With Claude

## Who I Am

I run a landscaping company with three crews. Most of my day is
routing trucks, quoting jobs, and keeping the crew schedule from
falling apart when someone calls out.

I am not a developer and I do not read code. Explain things in
plain language and do not assume I know the jargon.

## What I Am Working On

Our crew schedule is a whiteboard that gets erased every Friday. I
want a spreadsheet that shows who is on which job, and prints
clean enough to hand to a foreman.

## How We Work

Explain what you are doing as you go, so I learn while we build.

1. I give you the requirements.
2. You propose a plan and wait for my approval.
3. On approval, you deliver complete working files.
4. I test it and confirm.

Ask first, do not run ahead. When something breaks, gather
information before changing code.

## Always

- Show me the whole file, not just the part that changed
- Use the crew names we actually use, not Crew A and Crew B
- Tell me when something did not work

## Never

- Never delete a file without asking me first
- Never hand me something half finished and call it done

## Where My Files Live

C:\dev

## Session Management

- Update context/JOURNAL.md before I end a session.
- Tell me to use /clear after heavy work or big file reads.
- When in doubt, /clear. Ten seconds beats losing the session.

What a mature CLAUDE.md looks like:

A mature CLAUDE.md has all of the above plus some extras that evolve out of daily use:

• A "Brown M&M" rule — a small test at the top of your 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 your global one now. Start Claude Code in your Sandbox folder and ask it to create the file for you — you'll be standing in Sandbox, but the file lands in your user profile, so every future project inherits it. Hit Copy on the preview panel above to put your CLAUDE.md on the clipboard, then paste the short instruction below into Claude, press Enter twice for a new line, and paste your file right after it:

Your global 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.

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.

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

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

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