robots on payroll.

THE VAULT / START HERE / GUIDE + MARKDOWN

The Workspace Setup Kit

Lovable and Bolt are great training wheels, but the browser owns your work, meters your credits, and hides your files. This kit is the 30-minute bridge to a real local setup: install Claude Code (or Cursor), open a terminal for the first time, and run your first session. Every command is copy-paste, every step tells you what you should see, and every scary word comes with a plain-English translation.

LAST VERIFIED 2026-07-09

Leaving the browser is worth 30 minutes of mild discomfort

If you've shipped something in Lovable, Bolt, or Replit, you already know how to build: describe what you want, watch it appear, iterate. This kit doesn't change that. It changes where it happens, and that changes three things that matter.

What changesIn the browser toolsOn your machine
Cost controlCredits that vanish fast; heavy build days can run $50+ in top-upsClaude Code on the $20/month Pro plan covers a few focused hours of building every day, flat
Lock-inYour app lives on their platform; leaving means exporting and hopingNo platform to leave. Your project works with Claude Code today, Cursor tomorrow, whatever wins next year
Your filesCode hidden behind a preview pane you can't fully touchReal files in a real folder you own, back up, and open with anything

NOTE

Use this page as a prompt reference. Every file below is built to be handed straight to an AI. Download it, drop it into Claude, ChatGPT, Cursor, or Lovable, and say "use this as my playbook." The prompts on this page are copy-paste ready.

The only obstacle is the terminal (a text window where you type commands to your computer), and the obstacle is 90% reputation. You will use about 6 commands, all copy-paste, all in this kit. Think of it as a chat box for your computer: you type, it answers in text. You already talk to computers in text all day; this is the same skill with a worse font.

The setup: 5 steps, 30 minutes, Mac or Windows

The full walkthrough with every command, every "what you should see," and every "what if I don't" lives in setup-guide.md below. Here's the shape of it:

  1. 1

    Pick your tool (2 min)

    Claude Code is the recommended default: a coding agent in your terminal, included with the $20/month Claude Pro plan ($17/month billed annually). Cursor is the alternative if you want to see your files in a sidebar: $20/month Pro with a free Hobby tier. Prices verified July 2026. Pick one; you can switch later because your files are yours now.

  2. 2

    Open a terminal (3 min)

    Mac: Cmd + Space, type Terminal, Enter. Windows: Windows key, type PowerShell, Enter. You should see a blinking cursor waiting for you. Type echo hello, press Enter, and the computer says hello back. That's the whole skill.

  3. 3

    Make a projects folder (2 min)

    Run mkdir -p ~/projects then cd ~/projects (Windows: mkdir ~/projects then cd ~/projects). One folder where everything you build lives. The terminal says nothing when it works; silence is success.

  4. 4

    Install and verify (5 min)

    Mac: curl -fsSL https://claude.ai/install.sh | bash and Windows: irm https://claude.ai/install.ps1 | iex. Then open a fresh terminal and run claude --version. Any version number means you're in. The setup guide covers the two errors that actually happen.

  5. 5

    Start it and log in (5 min)

    Run claude inside your projects folder. First run opens your browser to log in with your Claude account. You land back in the terminal with an input box. Talk to it in plain English; that's the interface.

WATCH OUT

The one universal fix: when any step throws an error, copy the exact error text and paste it to an AI with "explain this in plain English and give me the single most likely fix as a copy-paste command." That one move resolves most setup problems in one round trip.

The CLAUDE.md: house rules that make the AI beginner-safe

Claude Code reads a file called CLAUDE.md from your project folder at the start of every session. It's a standing set of house rules, so you never have to repeat yourself. The beginner version in this kit is 5 rules and a diary habit, each one there because of a specific way beginners get burned:

The ruleThe burn it prevents
Explain what changed after every stepSessions where things happen and you learn nothing
One change at a time12 changes at once; when one breaks, every change is a suspect
Ask before deleting anythingThe one mistake that's genuinely hard to undo
Never touch .env without telling me (the file that holds secrets like API keys)Leaked keys and surprise bills, the expensive kind of oops
Keep a PROGRESS.md diaryThe AI forgets everything between sessions; the diary is its memory and yours. Next session opens with "read PROGRESS.md" and you're back where you left off

The file is annotated: every rule has a comment explaining why it exists, so you're learning the reasoning, not just copying rules. Rename it to CLAUDE.md, drop a copy in every project folder, done.

Your first 15 minutes with Claude Code: three prompts

Setup done, CLAUDE.md in place. These three prompts, in order, take you from "it's installed" to "something I made is on the internet." Paste them exactly.

Prompt 1: the tour (minutes 0-3)

PROMPT: TOUR MY PROJECT (paste into Claude Code)
Give me a tour of the current folder as if I've never seen a code project before.

1. List what's here (if it's empty, say so, that's fine).
2. For each file or folder, one plain-English sentence on what it does and whether I'll ever need to touch it.
3. Tell me which ONE file matters most for someone at my level, and why.
4. End with the single most useful thing I could ask you to do next in this folder.

Keep the whole answer under 20 lines. No jargon without a translation in parentheses.

Prompt 2: build a tiny page (minutes 3-10)

PROMPT: BUILD A TINY PAGE (paste into Claude Code)
Build me a single-file personal page: one HTML file called index.html, no frameworks, no dependencies (nothing that needs installing).

It should have:
- My name as a big heading: [YOUR NAME]
- One sentence about what I'm building: [ONE SENTENCE, e.g. "Building a booking tool for dog groomers"]
- A short list of 3 links I care about: [LINK 1, LINK 2, LINK 3]
- Colors and fonts with some personality. Surprise me, but keep it readable.

Rules for this session:
1. Build it in one file so I can see everything in one place.
2. When you're done, walk me through the file top to bottom in plain English: what each section does and which line I'd edit to change the text, the colors, and the links.
3. Tell me exactly how to open it in my browser.

Then wait. I'm going to change one small thing myself before we do anything else.

That last line is the point of the exercise. Open the file, ask Claude where the background color lives, change it yourself, refresh the browser. The moment your edit shows up on screen is the moment this stops being magic and starts being yours.

Prompt 3: put it on the internet (minutes 10-15)

PROMPT: PUBLISH IT (paste into Claude Code)
I want to put index.html on the real internet, for free, right now, with the least possible setup.

1. Recommend ONE way to do it (I've heard of Netlify Drop and Vercel; pick whichever needs the fewest steps for a single HTML file and no account complexity). Tell me why you picked it in one sentence.
2. Give me the exact steps as a numbered list: every click or command, nothing skipped. If a step happens in the browser, name the button I'm clicking.
3. Tell me what the free tier includes and at what point this would ever cost money, in dollars.
4. After I confirm it's live, add a PROGRESS.md entry recording what we built and the live URL.

PAYOFF

15 minutes in, you have: a working local setup, a page you built and edited, a live URL you can text to someone, and a PROGRESS.md diary already doing its job. That's the entire browser-to-local bridge, crossed.

What breaks most often (and the exact fix)

SymptomWhat it meansThe fix
command not found: claude after installingYour terminal hasn't noticed the new install yet, or it went somewhere the terminal doesn't lookClose the terminal completely and open a fresh one. Still failing? Re-run the installer and paste its final output into a Claude chat: "what do I run to finish this install?"
Red "execution policy" error on WindowsPowerShell being cautious about downloaded scriptsRun Set-ExecutionPolicy -Scope CurrentUser RemoteSigned, answer Y, retry the install command
Claude Code asks permission for everythingWorking as designed; it asks before touching files and running commandsSay yes to reads and file creation. Keep the asks for deletes; your CLAUDE.md demands that on purpose
Login loop: browser says success, terminal disagreesThe handshake between browser and terminal droppedCtrl + C to quit, run claude again. Second attempt almost always lands
The AI forgot everything from yesterdayNormal. Sessions don't share memory (each has a limited context window, the amount it can keep in mind)Start every session with: "Read PROGRESS.md and tell me where we left off." This is why the diary rule exists

When you outgrow this kit

Two signs you're ready for the next rung. First: your CLAUDE.md starts feeling thin because you now have real commands, real rules, and files that must not be touched. Graduate to the CLAUDE.md Starter, the pro version of the file you just installed. Second: you've built something you'd be sad to lose. That's your cue for GitHub for Normal People, which gives every project a memory and an undo button.

NOTE

The move: run the 30-minute setup today, then spend your first 15 minutes on the three prompts above. Everything after that is just building.

Get the next drop

Every new Vault system ships to the list first. Twice a week, free.