Book a check-upBook
Menu

Google Antigravity ward

Code review for code written with Google Antigravity

Antigravity's agents plan a task, write the code, open it in a browser to check that it works and hand you a walkthrough of what they did. The walkthrough tells you what the agent believes it did, not what the code does when it meets a real user.

I read the code instead of the walkthrough. You get a ranked list of what to fix, in plain English, with a fix prompt for each finding you can hand to the agent as its next task.

Book a check-up from $149Read a sample report

What Google Antigravity usually generates

  • Next.js
  • React
  • TypeScript
  • Express
  • Prisma
  • PostgreSQL
  • Firebase
  • Vitest
X-rayserver/routes/orders.ts1 fracture
app.get('/api/orders/:id', async (req, res) => {
  const order = await db.query.orders.findFirst({
    where: eq(orders.id, Number(req.params.id))
  })
  if (!order) return res.status(404).json({ error: 'Not found' })
  res.json(order)
})
  1. The agent opened this in its browser while signed in and saw the right order; there is no login check at all, so anyone can read every order by counting up the id.

Common problems in Google Antigravity apps

Not every app has all of these. The report tells you which ones yours has, where, and what to do about each.

  1. Critical

    Verified in the browser, open to everyone else

    The agent opened the page while signed in, saw the right data and reported success. It did not try the same URL signed out or as another user. I do, and I list every route that answers to people it should not.

  2. High

    Request bodies trusted because the form was trusted

    The agent built the form and the endpoint together, so the endpoint assumes it only hears from the form. It reads the body and writes it to the database as it came. I list each entry point and what a caller can change through it.

  3. High

    Subagents that each solved their part

    A task split across subagents comes back with two auth helpers, two ways of reporting errors and three opinions on what a user id is called. The seams between them are where the bugs live. I map them and say which version to keep.

  4. Medium

    Tests that confirm what the agent just did

    Tests written in the same task as the code tend to assert the implementation, not the requirement. They pass today and keep passing after the behavior breaks. I tell you which tests check something real.

  5. Medium

    Errors swallowed so the task could finish

    try/catch blocks that log and carry on, so the walkthrough ends without a red line. The payment that failed looks exactly like the one that succeeded. I trace each one to what it hides.

  6. Low

    Development defaults that reach production

    process.env.APP_URL ?? 'http://localhost:3000' works on the agent's machine. In production, one missing variable points your emails, redirects or webhooks at localhost. I check every fallback value.

Treatment plan

How it works

  1. Book a check-up

    Choose a tier and tell me where to send the report. Add your app's address if it is live. Two minutes, no sales call.

  2. Show me your code

    Pay by card, then give me read-only access to your code on GitHub (you paste in a key I send you) and let me into your app with test accounts. Never done that? I send you step-by-step instructions for your tool. I measure your app and confirm it fits before I start.

  3. Get your diagnosis

    Ready to launch, or not yet. Problems ranked, critical ones proven on your live app, each with a prescription for your AI tool. A PDF by email, then 7 to 30 days of questions by email.

  4. Fix it, then a free follow-up

    Fix the problems yourself, with your AI, or let me do it with the Fix Pack. Tell me within 30 days and I check once more that they are really gone.

Pharmacy

Pick your treatment

Same fixed prices, whichever tool wrote the code.

Check-up

Safety Scan

Is it safe to let real people in? The five things to fix first.

App size
Up to 20k lines of code
Ready in
2 business days

$149

Founding price for the first 10 customers, 10 left. Then $199.

  • A diagnosis: ready to launch, or not yet
  • The 5 problems to fix first, each checked by a human in your code
  • Every critical problem proven on your live app, with screenshots
  • Strangers in your users' data, leaked keys, payment holes, made-up packages
  • A prescription for each problem: a prompt for your AI tool
  • Discharge instructions for your AI, so it stops repeating them
  • 7 days of questions by email, so you are not alone with the report
  • A free follow-up check within 30 days, once you have fixed them
  • Want more afterwards? The price counts toward a Launch Review or Fix Pack within 30 days
Book Safety Scan

My
pick

Full exam

Launch Review

About to launch? Everything I find, and a call where I explain it.

App size
Up to 30k lines (50k: +$299)
Ready in
4 business days

$799

  • Everything in Safety Scan, including the free follow-up check of every problem
  • Every problem I find, not just the top 5
  • Logins, permissions and database rules, checked end to end
  • Will it survive real users? Speed, crashes and runaway costs
  • 30-minute video call where I explain it, no jargon
  • 30 days of questions by email
  • Bigger than 30k lines? +$299 up to 50k, and I tell you before I start
Book Launch Review

Surgery

Fix Pack

Don't want to fix it yourself? I do the fixing.

App size
Up to 30k lines of code
Ready in
5 business days

$1,499

  • A Safety Scan of your app, up to 30k lines of your code
  • A fix list with my time estimate. You approve it before I change anything
  • I fix the top problems myself, up to 6 hours of work
  • More to fix after that? I keep going at $199 an hour, only in blocks you approve first
  • Every change explained in plain English, with a "how to test this" note. Nothing goes live until you approve it
  • A second scan after the fixes, so you know they worked
  • 30 days of questions by email
Book Fix Pack

No idea how big your app is? That’s normal, and you never have to count anything. Book the review you want; I measure your app before I start and tell you. If it doesn’t fit, you choose: upgrade, narrow it down, or a full refund. “Lines of your code” means the code you and your AI wrote, not the packages and UI kit your tool installed; many apps built with Lovable, Bolt or v0 fit the Safety Scan.

Start small, upgrade later. The Safety Scan’s price counts in full toward a Launch Review or Fix Pack for the same app within 30 days of your report.

Why this price? Software does the first pass, so you pay for the part only a person can do: checking every finding in your code, proving the critical ones and deciding what matters for your app. I take at most 3 Safety Scans and 2 Launch Reviews (or one Fix Pack) a week; if this week is full, yours starts the next.

Prices in US dollars, paid once, no sales call and no surprise invoice: anything extra is your choice, told to you before I start. The clock starts when I can see your code. Reports arrive as a PDF by email, in English, or German if you prefer.

Need a few things fixed after a scan? I fix by the hour at $199, three hours minimum, with the list agreed before I start.

Bigger than 50k lines, or a real mess? Rescue jobs are quoted, from $3,000, no obligation. Email me.

Not for you if

  • you have a team of engineers who already review each other’s code,
  • your app’s backend isn’t JavaScript or TypeScript (Python Replit apps, for example), or it is over 100k lines,
  • you handle regulated data (health records, banking, children), or need a pentest, certificate or compliance sign-off. Taking card payments through Stripe is fine.

A review lowers your risk a lot. It can’t guarantee that your app is secure, and nobody honest will say otherwise.

Google Antigravity questions

How do I share code written with Antigravity?

Antigravity works on a normal local project, or on a Git worktree of one. Push it to a GitHub repository (or GitLab or Bitbucket) and give me read-only access (I send you a key to paste in; it takes a minute).

Can I apply the fixes with Antigravity?

Yes. Each finding comes with a fix prompt written for an agent, naming the files and the change. Hand it to the agent as a task, then read the diff yourself before you accept it. The agent's own walkthrough is a summary, not a review.

Will you tell me what to put in my rules?

Yes. Antigravity reads AGENTS.md or GEMINI.md and the .agents/rules folder. The report ends with a short list of rules for your project, so the next task does not reintroduce the same findings.

Why not just ask my AI to review it?

Do, and I will even give you the prompt. You will get a long list. What your AI cannot do is tell you which items are real, prove them against your live app, see your database and hosting settings, or check that its own fixes worked. If you cannot read code, that is the part you cannot do yourself either. It is what you pay me for.

I'm not a developer. Is this for me?

Yes, that is exactly who it is for. If you built an app with AI and cannot tell whether the code is any good, I check it and explain what matters in plain English. You never need to understand the code to act on the report: every problem comes with a prompt you paste into your AI tool. And you do not need to know what to ask. The report answers the questions you would have asked if you knew how.

How do I show you my code?

Most AI builders can push your app to GitHub, a free site that stores code. You give me read-only access by pasting a key I send you into your repository settings, which means I can look but not change anything. Never done it? After you book, I send you step-by-step instructions for your tool. A zip file works too. When the report is delivered, remove my access again; I remind you.

Is my code safe with you?

Every booking comes with an NDA, automatically. I never sell, publish or pass on your code. The only other party that sees it is the AI provider that helps with the first pass, under terms that do not allow it to train on your code. I never need your passwords or your live database, and I delete my copy within 7 days of delivering the final report.

Reviews for other tools

Find out what Google Antigravity skipped.

From $149 for the first 10 customers (10 left). Ready within 2 business days. If the Safety Scan finds no problem rated medium or worse, you pay nothing.

Book a check-upRead a sample report

Visiting hoursBook any time. I reply within one business day.