Everyone and their mom is talking about one GitHub repo right now.
It's called REA, and that stands for Reverse Engineer Anything.
You point Claude at an app you don't have the code for, and Claude figures out how it
works.
Then you can rebuild it from scratch for free.
It has over 149,000 stars on GitHub, but here's the weird part.
It's six months old, and for almost all of that time, nobody cared.
Last Wednesday, it had about
Last Wednesday, it had about 13,000 stars.
Five days later, it had 149,000.
So why is everyone talking about it now?
It blew up the same week someone used Claude
to build free copies of Photoshop and six other Adobe apps.
So people were already asking how far AI can go with copying apps.
REA showed up with an answer.
One post on X put it like this.
We spent years teaching AI to write software.
Now we're teaching it to
Now we're teaching it to take software apart.
When I first saw it, I figured it was a hacker tool I'd never touch,
but it actually answers a question I've been stuck on since my last video,
which was about those Adobe copies.
If anyone can copy an app, what are people going to pay for?
So here's a quick test you can run on your own product right now.
Ask yourself one question about whatever you sell.
If someone copied my product perfectly tomorrow, why?
Tomorrow, why would my customers stay?
Whatever your answer is, that's your moat.
A moat is just the thing that keeps competitors from copying you.
And if you can't answer that question, you first need to give your customers a reason to stay.
Maybe you answer their messages the same day.
Maybe you already know their business inside and out.
Maybe they just like working with you.
None of those have anything to do with your code.
Get one of those first before you worry about anyone copying your app.
app.
So I'll show you what REA actually does and who should and shouldn't touch it.
Then I'll give you the three things people will still pay for when anyone can copy anything.
The third one is the one I'm betting my whole business on.
If you like building cool things
with Claude, I co-founded the Claude Code Club.
That's where we build stuff like this together
and the links in my description.
Before any of that, you need to understand one thing.
Every app on your computer is a sealed box.
your computer is a sealed box.
Photoshop, Notion, the game you played as a kid.
You get the box, but you never get the code inside it.
For a long time, opening that box took a specialist and a lot of patience.
What the REA repo does is hand that sealed box to Claude
so Claude can open it up and see how the app works.
So what is REA really?
Well, REA is a free add on for your agent.
It works with Claude Code, Codex Cursor, Gemini CLI and a
Gemini CLI, and a few others.
It plugs in through something called MCP, which is just a way to give
Claude new tools.
Installing it is easy.
Just paste the GitHub link into Claude code and say,
install this for me.
Claude sets it up, and then you restart Claude code.
Pro tip, before you
install it, paste the same link and ask Claude what this repo does and how you could use it.
Now, Claude has a toolbox for looking inside apps, so here's how it works under the hood.
When a company ships an app, its code gets turned into machine code.
That's the ones and zeros your computer runs and a human can't read it.
There are other programs that turn machine code back into something a human can read.
The big ones are called Ghidra, Hopper and IDA.
Ghidra is free and fun fact, the NSA built it.
REA lets Claude drive those programs for you.
Claude asks a question.
REA digs into the app and it shows you the exact spots in the app that prove its answer.
app that prove its answer so you know it isn't guessing.
It also tells you what it couldn't
figure out.
Think of it like a chef at a restaurant.
Normal coding with Claude is cooking from a
recipe card.
You have the formula so you can make it.
REA is the chef who can figure out the entire
recipe and every ingredient from a single bite.
The example prompt in their own repo is simple.
You type this into Claude.
Understand how search works in the Notes app, show me the evidence,
and build a similar feature for my project.
feature for my project.
Swap notes for any app and swap search for any feature you like.
The last part is the line that got everyone talking.
Build a similar feature for my project.
Another pro tip is give Claude screenshots of the feature you want or tell it to open the app
and look for itself.
The more Claude can see, the better it does.
So how far can it actually go?
The use cases people have come up with are wild.
So what are people actually building with it?
with it?
Well, here are three real examples.
The first use case comes from a developer named
Mukesh Murigan.
He pointed REA at the color picker in Power Toys, which is Microsoft's free
toolkit for Windows.
He only gave Claude the finished app, not the code.
But Microsoft's code
for that app is public, so he could check REA's answers against what Microsoft actually built.
REA got eight out of nine findings fully right.
Then he used what it found to build his own color
picker in under 750 lines of code.
lines of code.
The second use case is a game called DX ball.
It's a brick breaker game from
the 1990s.
One developer even used REA to find the exact math the game uses to move the sound
from your left speaker to your right as the ball moves.
Then they rebuilt that math from scratch.
The rebuilt version matched the original game in all 3,205 tests down to the exact
bytes.
That's a 30 year old game rebuilt without ever seeing its code.
And the third
seeing its code.
And the third use case is the one that made me stop scrolling.
Another developer
pointed REA at a free trial of QuickBooks, the accounting app.
Then they built their own open
source accounting app with invoices, bank imports, and reports.
Even they say REA didn't hand them
the original code or a finished product in one step and that it took real work.
But think about
that.
One person studied a paid app that's worth billions of dollars and built their own version of
and built their own version of it.
And it goes way past desktop apps.
The repo lists websites, Android apps,
the code inside devices, and even crash reports.
Now, some people on X say a lot of those stars are just hype,
people clicking a star to save it for later, and that's fair.
But the downloads tell the same story.
In September, the install package
got downloaded about 100 times a week.
Last week, it got downloaded 128,470 times.
So people aren't just starring it,
So people aren't just starring it,
they're actually installing it.
But just because you can point REA at any app
doesn't mean you should.
So should you install it?
I'll give you my honest take,
and it might not be the one you expect.
Think of REA like a locksmith set of picks.
Owning one is legal.
What you open with it is the part that matters.
The makers are really clear about this.
REA is for security, research, learning,
making your own app work with other apps,
saving old software, and checking software you own.
Their own rules say they won't help you break copy protection,
build game cheats, or copy someone else's paid software.
So that QuickBook project sits right in the gray area.
Studying how an app works is one thing,
copying it is another,
and trying to sell your own copy of someone else's product
is a major red flag.
And reverse engineering an app can break its license agreement
depending on where you live and what you agree to.
I'm not a lawyer, so if you're doing this for a business,
for a business ask one so who should use it if you do security work this was built for you if your
company still runs an old tool and nobody has the code anymore this is huge for you and if you want
to understand how a feature works so you can build your own version it's an amazing way to learn so
who shouldn't use it if you haven't shipped your first project with claude yet skip it for now the
deep stuff needs extra programs like hopper or gidra and it gets technical fast i've never written
I've never written a line of code by hand in my life.
I build with Claude every single day, and I'm still not the main user for this tool.
So for most of you, the tool itself isn't what matters.
What it means for the apps you build is what matters.
Because REA isn't the only repo like this.
A couple of days ago, I made a whole video about another one called Artcraft.
And when you put Artcraft and REA together, it all comes down to one simple question.
If anyone can copy anything, what are people actually going to pay for?
actually going to pay for?
To answer that, you need to see what Artcraft pulled off.
An engineer named Brandon Thomas used Claude to build free open source copies of seven Adobe
apps, including Photoshop, Premiere, and Lightroom.
The Photoshop copy alone got over 24,000 stars on
GitHub in eight days, and his team never touched Adobe's code.
They rebuilt every app from scratch
using public documents and by studying how Adobe's apps look and behave.
If you want the full
breakdown of all seven apps.
I'll link that.
of all seven apps, I'll link that video right here.
So put those two repos side by side.
Artcraft never opened Adobe Sealed Box.
They rebuilt the apps from scratch from the outside.
REA opens the box and looks inside
all the way down to the machine code.
So now Quad can rebuild an app from the outside
and look at one from the inside
so there's not much left of an app that stays hidden.
Now, are the copies as good as the real thing?
Not yet.
Artcraft's own team says their Photoshop copy
Photoshop copy isn't ready for daily professional work, but the cost of copying an app just
dropped like a rock and it keeps dropping.
So back to that question.
If anyone can copy anything, what are people going to pay for?
And honestly, the answer was sitting in my own business the whole time.
The Quad Code Club is $9 a month and has over 8,000 members.
And there's a lot of content about Quad Code on YouTube for free, but people pay anyway.
So why?
Why?
Because they like the way we teach.
Because they like the way we teach, so they trust us.
And free YouTube is a lot of noise.
You watch 10 different people and you still don't know what to do first.
Inside the club, you get a clear structure and you know exactly what to focus on next.
So they believe the club gets them better results in less time and with less effort,
and they feel more sure it'll actually work.
So the content was never the thing they were paying for.
So here are the three things they are paying for
and the three things people will still pay for when anyone can.
pay for when anyone can copy anything well the first thing people will still pay for is the result
picture two products built on the exact same code one is a 49 a month app that helps you write
linkedin posts the other is 500 a month and it books sales calls for you from linkedin the code
underneath is the same but one charges 10 times more the first one sells a tool and anyone with
Claude can copy a tool.
The second one sells a result, and a result
a result and a result needs someone who knows what works,
keeps tuning it and stands behind it.
The closer you get to the money your customer actually wants,
the harder you are to copy.
Think about photos.
Your phone made taking a photo free,
but wedding photographers still charge thousands
because couples pay for the day to be captured right
by someone they trust.
And that word trust leads right into the second thing.
The second thing people will still pay for
is someone who answers when it breaks.
answers when it breaks.
Say you run a business doing $2 million a year.
Remember that QuickBooks
copy from earlier?
You can run your books on a free accounting app that a stranger rebuilt from
a trial.
Or you can pay for the real one with backup support and a phone number.
Your numbers
come out wrong the week your taxes are due.
Which one do you want?
Free code is cheap until it
breaks.
Then it's the most expensive thing you own.
So as apps get easier to copy, the person
standing behind the app gets more valuable.
That's the second thing.
But the third one matters more than both, and it's the one I'm betting my whole business
on.
The third thing people will still pay for is you, and the people who already trust you.
Picture what happens next.
When anyone can build an app in a weekend, there won't be 10 apps for every problem.
There will be 10,000.
So the hard part stops being building the thing.
The hard part becomes getting anyone to care.
The person who already has an audience, a community, or a list of customers who trust them
customers who trust them wins that game.
They can build something on Monday and have buyers by Friday.
That's why I spend my time on YouTube and in the Cloud Code Club and almost no time worrying about
someone copying my stuff.
Someone could copy every lesson in the club tomorrow.
They can't copy the
8,000 people in the club who already know me.
So does all this mean software is dead?
No.
It means
the part of an app's price that came from this was hard to build is going away.
And the result,
the support, the trust behind
the support, the trust behind an app, and your ability to get traffic and win customers are all
getting more valuable every month.
So here's the recap.
REA lets Claude look inside apps without
having the code.
Use it if you do security work, rescue old software, or want to learn how a feature
works.
Skip it if you're just getting started.
And when anyone can copy anything, people still
pay for three things.
They pay for the result, for someone who answers when it breaks, and for
the people who already trust you.
already trust you.
So here's your one thing for this week.
Ask the question from the start of
this video.
If someone copied my product perfectly tomorrow, why would my customers stay?
Write your
answer down in one sentence, then check your product against the three things people still
pay for.
First, can your customers point to a real result like more sales or hours saved every week?
Second, if something breaks, do they know they can reach you and get it fixed?
And third,
Do people already know and trust you?
And do you have a way to get in front?
you have a way to get in front of new customers.
Every yes is part of your moat.
Find the one that's a no and spend this week fixing it.
And if you want to build things with Claude
that people will actually pay for,
that's what the Claude Code Club is for.
It's a step-by-step path to master Claude Code in 45 days
and it has lessons on turning what you build
into something people pay for.
It's $9 a month and the link's in the description.
Anyone can copy your app now,
nobody can copy the people who trust you.