How to Build an App With Claude Code as a Non-Developer: A Safe 7-Step Method

Yes, you can build a small, real app with Claude Code without being a developer. Claude Code is an AI agent that works inside a folder on your computer. It reads files, writes code and runs commands, and it asks you before it acts, depending on the permission mode you choose.

What decides success is not code. It is three habits: keep the first version small, write down what "done" means, and check the work before you trust it. That last habit matters. In one test of more than 100 AI models on 80 coding tasks, the generated code had a security flaw in 45% of cases (Veracode, 2025). And in 2024 alone, about 23.8 million passwords, keys and other secrets were added to public code on GitHub (GitGuardian).

Many guides online skip those risks. Some use an old install command. One commits its files before it hides the secret file. Some never mention that Claude Code needs a paid plan. This guide gives you the full path, from idea to a first version you can safely show people.

We use one made-up example throughout: Northwind Services, a small cleaning company. Its owner wants a page where office staff can price a cleaning job in 30 seconds instead of 5 minutes.

Before you start: what you need

• A paid plan. The official setup page says Claude Code needs a Pro, Max, Team, Enterprise or Console account, and the free plan does not include it (Claude Code setup). At the time of writing, Pro costs $17 per month billed yearly, or $20 billed monthly (pricing). Check the current price before you buy.
• A computer with macOS 13 or later, Windows 10 (version 1809) or later, or a recent Linux, and at least 4 GB of RAM (setup).
• About one week of evenings for a first small app. Plan for the first two evenings to go on scope and setup, not code.

Step 1: Cut the idea to one week

Most first projects fail because they are too big. Write your idea in three lines: what it is, who uses it, and the one job it does. Then sort every feature into four boxes:

Build only Must and Money in week one. Notice what the Northwind cut does: version one stores no personal data and takes no payments. That single choice removes most of the serious risks. Add logins, payments or customer details only after the first version works and someone has reviewed it.

Step 2: Write a one-page spec with done-checks

A spec (some people call it a PRD) tells the agent what to build. The most important part is the list of checks that prove the app is done. Each check must be something you can test by hand in under a minute.

SPEC: NORTHWIND PRICE ESTIMATOR (v1)

Goal: office staff price a cleaning job in under 30 seconds.
User: office staff, on a laptop or phone. No login.

Must:
- Choose number of bedrooms (1 to 5) and bathrooms (1 to 4).
- Tick extras: oven, windows, fridge.
- See the total price, updated as you change choices.
Prices: [paste your price list here]

Never in v1: customer names, emails, phone numbers, payments,
logins, a database.

Done when ALL of these pass:
1. 2 bedrooms + 1 bathroom, no extras shows [expected price].
2. 3 bedrooms + 2 bathrooms + oven shows [expected price].
3. Changing any choice updates the price at once.
4. The page works on a phone screen without sideways scrolling.
5. No price appears anywhere except the prices listed above.

Work out the expected prices yourself, with a calculator, before the build. If the app shows a different number, the app is wrong, not your sum.

Step 3: Install Claude Code and make a project folder

Install it with the official command for your system (setup). There is also a desktop app if you prefer not to use a terminal.

# macOS, Linux or WSL
curl -fsSL https://claude.ai/install.sh | bash

# Windows PowerShell
irm https://claude.ai/install.ps1 | iex

Open a new terminal window and check that it worked:

claude --version

A version number means it worked. Some older guides tell you to install with npm and an old Node.js version. Follow the official page instead, because it changes.

Now make one folder for the project, start git in it, and start Claude Code there. Git keeps a saved history of every working version, so you can always go back. If git is not installed, ask Claude Code to explain how to install it on your system.

mkdir northwind-estimator
cd northwind-estimator
git init
claude

The first time, Claude Code opens a browser window to log in. Then copy your spec into a file in the folder called SPEC.md.

Before your first commit, hide the secret file. Ask Claude Code: "Create a .gitignore file that lists .env, and show me the file." Check that the file exists. Rules in the instructions file (next step) are guidance the agent usually follows, not a lock, so always check this yourself.

Step 4: Write the instructions file

Claude Code reads a file called CLAUDE.md at the start of every session. Put your project rules there. The command /init creates a starter version, and the docs suggest keeping each file under 200 lines, because longer files are followed less well (Claude Code memory docs). Other coding agents use a similar file, often called AGENTS.md.

Here is a starter for a non-developer. Paste it in and edit the first section.

# Project: Northwind price estimator

## About me
I am not a developer. Explain every step in plain English,
in 3 sentences or fewer, before you do it.

## The spec
SPEC.md is the source of truth. Do not add features that are
not in it. If you think something is missing, ask me.

## How we work
- One small task at a time. After each task, tell me exactly
  how to test it by hand, then stop and wait.
- Prefer the simplest setup that works. Ask before adding any
  new tool, service or library.
- Never delete files or folders without asking me first.

## Safety rules
- Never put passwords, API keys or tokens in code files.
  Keep them in a .env file, and make sure .gitignore lists
  .env BEFORE the first commit.
- No personal data and no payments in v1.
- If a fix fails twice, stop and explain what you think is
  wrong, instead of trying a third guess.

The last rule saves hours. An agent that keeps guessing can make a small problem bigger.

Step 5: Build in small loops

Use the same loop for every feature. One loop should take 10 to 30 minutes.

1. Plan first. Switch to plan mode (press Shift+Tab until it shows plan mode). In plan mode, Claude Code cannot edit files until you approve a plan (permission modes). Ask: "Read SPEC.md. Propose a plan for the first Must item only. Keep it simple."
2. Read the plan. If you do not understand a step, ask. If it adds things you did not ask for, say no.
3. Build. Approve the plan. For your first projects, use Manual mode, which asks before most edits and commands, so you see each action. Newer versions start in a mode called auto, which does not ask you first. Look at the mode label near the prompt and press Shift+Tab until it says Manual (also called default). Do not use the mode that skips all permission checks. The docs say it is for isolated containers and virtual machines only (permission modes).
4. Test it yourself. Open the app and try the done-checks for this feature. Do not accept "it should work now". Click it.
5. Save a working version. When it works, ask: "Commit this to git with a short message."

If a step goes wrong, type /rewind, or press Esc twice while the prompt box is empty, to go back to an earlier point in the session. But know its limits: rewind does not undo file changes made by terminal commands, and the docs say checkpoints are not a replacement for version control (checkpointing). Your git commits are your real safety net.

When something breaks, be specific. Not "it's broken", but: "When I pick 3 bedrooms and tick oven, the price shows [wrong number]. The spec says [right number]. Find the cause and explain it before you change anything."

Step 6: Check before you call it done

When every Must item works, run a full check in a fresh session, so the reviewer does not defend its own work. Start a new Claude Code session in the same folder and paste:

You are reviewing this project before it is shown to anyone.
Read SPEC.md and all code files. Do not change anything.
Report:
1. Each done-check in SPEC.md: pass, fail, or cannot tell.
   Say how you checked.
2. Any feature in the code that is not in the spec.
3. Any password, key, token or personal data in the code,
   and whether .env is listed in .gitignore.
4. Anything that would break on a phone screen.
5. The 3 biggest risks, in plain English.

Then do your own check by hand:

• Run every done-check yourself, on a laptop and on a phone.
• Try silly inputs: tick everything, untick everything, reload the page.
• Ask a colleague to use it without help, and watch where they get stuck.

Fix what fails, commit, and check again.

Step 7: Share it safely

To share the app, you need to put it online, which is called "deploying". Ask Claude Code to explain your options and their costs in plain English, and pick one with a free tier for a first version. Before you deploy:

• Keep the code private. If you store it on a code-hosting site, make the repository private.
• Check for secrets one last time. Ask: "Search the whole project, including the git history, for passwords, keys or tokens." A key that reached git history stays there even after you delete it from the file. If one did, treat it as leaked: cancel it and make a new one.
• Start with a small group. Share the link with your own team first. Fix what they find.

When to bring in a developer

Pay for a review by an experienced developer before any of these:

• Real users log in.
• The app takes payments.
• The app stores personal data, such as names, emails, phone numbers or addresses.
• The app handles health, money or legal information.
• The same problem survives three focused attempts to fix it.

A short review at these points costs far less than a leak or a lost customer.

Common problems and quick fixes

---

This page is the short version of a longer process. The Builder's Toolkit covers it in 7 modules for non-developers who build with AI coding agents (Claude Code, Codex or Cursor): an idea pressure test, a PRD template with acceptance checks, instruction and skill file templates, a build agent plus a review agent, a check-before-done list, a launch checklist, and outreach scripts for the first customers. Each module has templates, checklists, copy-paste prompts and a worked example from a real product on the App Store. It is a pre-sale: modules 1 to 3 are ready now, and modules 4 to 7 ship by 28 October 2026. If this page is enough to get your first app built, start here.