21:11Pat Simmons · Demo
I Made Opus 4.8 and Fable 5 Build the Same App (RAW RESULTS)
Three identical one-shot prompts. Two models. The gap was not close.
June 11thThe argument in one line.
A structured agentic pipeline — recon, extraction, design spec, build, QA loop, deploy, customize, MCP — closes the gap between AI slop and a production-quality SaaS clone, making software ownership the default path for anyone who can prompt.
Read if. Skip if.
READ IF YOU ARE…
- You pay monthly SaaS fees for tools like Linear, Notion, or Trello and want to own an equivalent you can fully customize.
- You already use Claude Code or Cursor and want a repeatable system beyond one-shot prompting.
- You build internal tools for clients or teams and need to go from brief to deployed app fast.
- You want AI agents to control your own apps without depending on vendor-supplied MCP servers.
SKIP IF…
- You need Linear's full collaboration ecosystem, integrations, or enterprise compliance — the clone replicates the UI, not the backend.
- You have no prior experience with AI coding assistants; the system assumes comfort with Cursor and Vercel.
The full version, fast.
Naive AI cloning fails because the model has no structured evidence about what it is building. The fix is a five-phase context pipeline: automated screenshot recon of every UI state, CSS/token extraction via the Claude Chrome extension, a portable design.md spec, a single-agent build pass, and a QA sub-agent loop that grades pixel accuracy against the live site until it approves. Two final phases complete the arc: Vercel deploy in one agent command, and an MCP server so Claude can create and update issues in your clone without touching the UI. The full system is on GitHub.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Create a free account →Where the time goes.
00:00 – 00:50
01 · Intro
Side-by-side reveal of Linear and the afternoon clone; thesis stated
00:50 – 01:28
02 · Why AI clones come out as slop
Naive single-prompt output shown: broken purple dashboard, wrong avatar, dead buttons
01:28 – 02:05
03 · The system
Introduces clone-app-pat-pro and its 8-phase pipeline
02:05 – 05:38
04 · Step 1 — Recon
Chrome extension walks every route and interaction state; feedback loop catches missed hover and detail states
05:38 – 06:45
05 · Step 2 — Extraction
Reads computed CSS, downloads real fonts and icons; produces states manifest doc
06:45 – 08:25
06 · Step 3 — Design.md
Converts raw extracted values into a portable design system file; portability explained
08:25 – 11:02
07 · Step 4 — Building
Single-agent first pass; localhost comparison shows approx 90% fidelity out of the gate
11:02 – 14:39
08 · Step 5 — QA Loop
Detailed feedback triggers sub-agent QA cycle; translucency and toolbar issues resolved
14:39 – 15:26
09 · Step 6 — Deploying
One agent command deploys to Vercel via pre-stored API key; live URL confirmed
15:26 – 16:11
10 · Step 7 — Making It Yours
Screenshots Linear's paywalled Insights dashboard; prompts agent to build it in
16:11 – 18:35
11 · Step 8 — MCP Server
One prompt builds API endpoints and MCP server; agent creates an issue in 2 seconds; live refresh confirms
18:35 – 19:10
12 · Outro
GitHub repos linked; next video teased on agent configuration
Lines worth screenshotting.
- Naive AI clones fail not because the model is weak, but because it has no structured evidence package — screenshots, CSS tokens, and a design spec change the output entirely.
- The Claude Chrome extension can walk a live web app, click every interaction state, and export screenshots automatically without any manual browser work.
- A design.md file is a portable protocol: drop it into GPT, Gemini, or Claude and any coding agent builds in that visual language without re-extracting anything.
- Sub-agent QA loops outperform human review cycles — the implementation agent builds, the QA agent grades pixel accuracy, and the loop closes without human intervention.
- Owning your clone means you can unlock paywalled features yourself: screenshot the locked UI, paste to the agent, and build it in.
- Storing a Vercel API key in your agent lets it deploy to production in one sentence — no UI, no GitHub connect, no manual steps.
- Building your own MCP server on a self-hosted app costs a single prompt in 2026; a year earlier it would have been a week-long project.
- The design.md you generate from one app is reusable: port a billion-dollar company's visual design into any future project by referencing a single file.
- An AI agent controlling a self-hosted app has no rate limits, no permission walls, and no vendor dependency — that is the real endgame of cloning.
- The check-in gate after each phase is deliberate: human steering between phases catches the 5% of states automated recon misses before they compound downstream.
Why structured context beats a smarter model.
WHAT TO LEARN
The gap between an AI-generated mess and a production-quality app is not model capability — it is the quality of the evidence package you give the model before it writes a single line.
- A single naive prompt gives an AI no structural evidence — it has no idea what the real app looks like at every interaction state, so it guesses and gets it wrong.
- Automated recon — screenshotting every route and modal — costs you nothing but a prompt; it hands the model the specific visual context it needs to match pixel-level fidelity.
- Extracting CSS tokens before building means the clone uses the real color values, exact font files, and actual spacing units — not approximations the model hallucinated.
- A design.md file captures that extracted system in a portable format: reuse the same visual language across future projects or hand it to any coding agent without re-extracting.
- A QA sub-agent that diffs output against the original catches regressions you would never catch in a human review pass — and it loops automatically until the diff clears.
- Storing your deployment credentials in the agent eliminates the entire manual deploy cycle; the agent handles Vercel configuration as part of the same session.
- Building your own MCP server means you own the integration layer — no rate limits, no vendor permissions, no dependency on a third party to keep their MCP current.
- Owning the codebase lets you unlock paywalled features by simply screenshotting the locked UI and prompting a build; you are no longer subject to the vendor's pricing decisions.
Terms worth knowing.
- design.md
- A markdown file that encodes a full design system — colors, typography, spacing, gradients, components — in a format any AI coding agent can read and build from, regardless of model or IDE.
- states manifest doc
- A compiled output of every CSS computed value, color token, font, and iconography asset extracted from a live website — the raw evidence layer before it is cleaned into a design.md.
- QA loop
- A multi-agent cycle where implementation agents build and QA agents compare the output pixel-for-pixel against the original, returning a diff until the QA agent approves.
- Claude Chrome Extension
- A browser extension that gives Claude Code direct access to a live web page — enabling automated clicking, screenshot capture, and CSS inspection without manual browser interaction.
- MCP server
- A Model Context Protocol server that exposes your app's CRUD operations as callable tools, allowing any AI agent to create, read, update, and delete records through natural language.
Things they pointed at.
02:40toolClaude Chrome Extension
Lines you could clip.
00:00
“Everything down to the radial gradient inside the buttons has been more or less replicated.”
01:43
“A separate set of agents will go in and grade that copy against the real Linear, pixel for pixel, and then keep fixing those differences until they match.”
09:09
“Jesus. I honestly thought I was on Linear for a second.”
16:41
“If I'm clicking around UIs, that is just so 2025.”
17:42
“We've built an entirely agentic platform in just a few prompts.”
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
analogystory
00:00This is Linear. It's worth 1 and a quarter billion dollars with a b, and not only is it beautiful, it's an incredibly useful product management tool. Now this, this is an app I bytecode with Claude Code in an afternoon.
00:09Everything down to the radial gradient inside the buttons has been more or less replicated. So in the next eighteen minutes, I'll show you exactly how I cloned linear and how you too, using a custom system that I built, can clone pretty much any sass you want without writing a single line of code. Cue the sasspocalypse fear mongers.
00:25Now before we get started, I just wanted to say yes, I know we're not going to clone this and suddenly become linear and make a billion dollars. The point of this video though is to not necessarily profit, but rather to show you how easy it is to replace a lot of the software in your stack, save yourself a ton of money, and then make it completely yours by customizing it.
00:42And I really wanted to show off this system that I have built that you can use yourself and just make building your own software a bit easier. So let's get into it. Now normally, if you want to copy an app or copy certain parts of it, you would just open up the AI and tell it something like copy this.
00:57You may have tried this yourself and we've probably seen is what the AI comes back with is generally pretty sloppy. This is exactly what happened when I went to Claude and told it to copy linear. So it says the linear clone is complete, but if we go to local host, uh, we can see that it is pretty sloppy.
01:14We have just random purple here. There's emojis. It's not a proper circle for the user avatar.
01:20Obviously, we can't click any of these. If we compare this to actual linear, we can see it's much cleaner dashboard. So that is where this system here comes in.
01:28This is clone app, Hat Pro. It'll be available for you in the description, and I'll walk through in a second how we clone this and actually use this system. But the way it works is it will first go through the live site and the code behind it and captures everything we can, the colors, the spacing, the gradients.
01:44We then have an AI analyze all of it and build the copy. Then a separate set of agents will go in and grade that copy against the real linear, in this case, pixel for pixel, and then keep fixing those differences until they match. So it'll go into a loop until finally the QA agents approve the implementation agents and it's ready for me to review.
02:03So let's actually just do that now, start cloning. So once you have access to this repo, you can just go here, copy this or just copy the URL and feed it into your agent. We'll go back to cursor.
02:14We have a new session open with Claude code. And just tell Claude, clone this website's dashboard.
02:20Use the skill here. And then I'm also just going to say, make sure all UX is mapped out and everything is clickable.
02:28And they'll hit enter and then let this thing run. So it has cloned the repo. In other words, opened up the system as a whole.
02:34It is logging in to linear first via the URL I gave it with the Claude Chrome extension here. I'll talk all about that in a second. But it's just going through right now, and the first step is for you to just get a feel for the app.
02:47So it's taking a bunch of screenshots. It's testing a bunch of different states, and then it's just saving those all to a dedicated folder for our future agents when they actually go in and clone this to access. Here's what it found so far in this recon step.
02:59I've discovered the routes and confirmed, dark fame, retina, viewport, routes, inbox, my issues, reviews, projects, views. So it's gone through and it's clicked through. If we go back to the Chrome extension, you can see it's clicking through all these different views on the side panel and it's going through the app one by one.
03:13So we just finished the first phase recon and after each phase, it will check-in with us. So we can now go into the screenshots that are saved in our folder here. In cursor, we just open up this tab here, then under linear, then under recon, and under screenshots, then we have all of these different screenshots that we're taking.
03:29So we have the actual issues here. So we just zoom in on some of these. It's going through and it's taking screenshots one by one.
03:35So that is the active issues. Here is another view of the all issues. Here is another view of the backlog.
03:42It even selected different views like the Kanban board in linear. And we also have these interaction states, are super important as well. So we have things like the command menu.
03:51When you hit control k, that's showing up. So a screenshot of that, it has another create issue modal. So it seems like for the most part, it covered off on all of these different states, but I'm just gonna go back to linear and see if it missed anything.
04:02So the last thing is this this workspace menu as well. So it looks like this settings and then any of the hover states. Doesn't look like it got any of the hover states.
04:10So I'm thinking it missed a couple of these. And this is the beauty of this system as a whole, an ability to steer it through feedback after each phase. So that's exactly what we're gonna do.
04:18I'm gonna give a few points of feedback here by just going back to linear and just clicking around. And then one thing I don't think it captured was an ability to, when you click in, to see this view. So I'm gonna tell Claude that.
04:29Go back to cursor and say, okay. We're very close. I need you to continue to another round of recon.
04:34What you're missing is when you click into a linear issue. So you go issues, then you click into it.
04:40You can see this bread crumb shows up, the properties on the side, the assign, the labels, the project. So I need you to click all of those interaction states as well. Make sure you're not missing any of those, as well as an ability to update the issue.
04:52So typing into this and then even the, um, what do you call this? This pane that shows up at the top for formatting. So I need you to spawn the agents and go through another round of recon to make sure we haven't missed anything.
05:02So it's going back in and this is it clicking right now. It's highlighting this. It's clicking these properties on the right hand side, just taking a bunch more screenshots.
05:10Okay. The agent is telling me that round two recon is done. Click through every issue detail.
05:15It pulled up all these different screenshots. Save with these file names. So if we go back, you can see all of these different interaction states have now been added.
05:22I'm not gonna click through all of these. Think though, if I just see one, yep, it's getting all of those states that I mentioned. So now it has a nice comprehensive view of the entire app through all these screenshots.
05:34But seeing the app through screenshots can only get the AI so far when it's trying to clone. What we need to do now is get super scientific with this. Extraction is the next step.
05:42This is where it goes through everything it captured and reads the live code. And the way it does this is with the collab chrome extension again. So the CSS, the exact colors, the spacing down to the pixels, gradients, and it's downloading all of these real fonts, iconography images, all of that to really closely mimic as much as possible.
06:00Now it doesn't get everything. There are some things you just can't pull out of the code, but between the code and the screenshots, it has enough to compile a very close replica. Basically, full definition of what it takes to rebuild this app.
06:12So that's what we're gonna do right now. Have to proceed with step two. And in about ten minutes, we have part two extraction complete.
06:19And in this step, it created what's called a states manifest doc. Essentially, all of the code it could find, it could extract from linear. So if you've ever right clicked a website and hit inspect elements let me just show you that now.
06:30If we go back to linear, we go command shift I, these elements, the computed styles, that's exactly where it's pulling from. But now we just have a giant pile of values and a bunch of screenshots, not really usable yet. So what it needs to do is turn all of this into something we can actually build from.
06:45And that next step is coming up with a design spec, what's called a design dot m d. You might have seen these before. It's becoming the kind of standard portable way to describe a design so any coding agent can build from it.
06:55And so what it's doing right now, if we go back to cursor and tell it to proceed with the next step, proceed with step three. So it's now taking all those raw values and turning it into one clean design system. So the official colors, the type, the spacing, the components, everything that goes into linear.
07:11And in a couple more minutes, we've got our design spec ready, the design dot m d with the whole visual theme, colors, iconography, typography, components.
07:20I mean, we've even got it down to, like, gradients and shadows. If we actually go to this folder here where the design m d is located in this design spec, we can take a closer look at everything included. Now I recommend you parsing through this.
07:32I mean, some of this isn't just going to make any sense like color tokens, but just do a quick once over and make sure that everything is captured across the board. To me, this all looks good. So we can proceed with the next step.
07:43And the beauty of a design dot m d is I can reference it later. Say I wanted to build new pages in this linear clone to kinda customize this linear clone more, or I could bring this whole design style into a completely different project. So say I wanted to, I don't know, build a voice transcription app.
07:59What I could do is I could take this linear style that we just cloned and then drop in the design dot m d, and it's basically a protocol. It'll carry over anything to that coding agent, whether it's, you know, GPT, whether it's Gemini, whether it's Opus, and we'll build out that new app in this style, in this design dot m d kind of linear style that we've defined.
08:18So now we've got everything in place, but we still haven't written a single line of code. None of this is actually built yet. So how do we put this all together?
08:25Now we're getting to the fun part. So once I approve that design spec, we can go back to the agent and say approved, move to step four, and it will start coding. So it's gonna take everything we set up in the earlier steps and then write the whole app out in the code, and it's just gonna build this piece to piece together.
08:40So the screenshots it's going to use, it's gonna use the code that we extracted and the design dot m d as another reference point. And in a couple minutes, we'll have this app more or less built out. See how incredibly easy this is.
08:52Right? It just had to do a quick architecture check-in, which it did, and it wrote this whole file tree and component map. You don't really need to worry about that.
08:58I'm not even gonna look at this. Uh, we'll just say proceed. And we've got a first version of our build.
09:03So let's check it out at local host thirty fifty. Open a new tab here. Jesus.
09:09I honestly thought it was on I was on linear for a second. So that's linear. Let's already just do a comparison.
09:14Issues. Issues. Boom.
09:16Boom. I mean, it got you can see the icons are the same. Looks like it missed projects.
09:22For whatever reason, that icon isn't showing up. The iconography is about the same. The, like, placement of the tabs just being kind of tabbed over is missed, but this is like little nitpicky stuff.
09:32But let's actually, like, click around too and see how it looks. It even brought in this linear diffs little announcement here. Linear diffs.
09:40Linear diffs. So let's click into an issue. Import your data.
09:44Let's look at the right hand side panel properties. Very close. It's just translucent for some reason.
09:50Same with that. Same with that. Same with that.
09:53Looks like all the labels are there. And then does this? Okay.
09:56That doesn't work either. Breadcrumbs, those work.
09:59Backlog. Projects. What does projects look like in linear?
10:03Pretty darn close. Views. What does views do?
10:07Views doesn't do anything. I don't even know what views is if I'm being honest. Create custom views using filters to show only the issues you wanna see.
10:14I don't think we need that, but yeah, that's a that's only a nice to have. And then we have projects here. I can't even tell which one I'm on.
10:20Okay. I'm I'm on linear there. Projects here, issues, what happens when we go command k, command palette.
10:25Pretty good. What is linear is just a little bit better looking. I like their shading.
10:31It's pretty darn close there. What else? Okay.
10:34Actually creating an issue. I keep choosing the wrong app. Okay.
10:37We're on linear. Okay. There it is.
10:39Back to linear. Okay. All this filtering.
10:41Does this work? Oh, it's so close. It's just translucent for some reason.
10:46Oh, nice. We got a nice little Kanban board. I think linear does that too.
10:49Board. I mean, look how close this is. You know, granted we're not making an incredibly complex app, but to just one shot this output is pretty darn impressive.
10:58It's usually, honestly, not this accurate on the first go. I have this system set up to where it shouldn't be that great because it's only one agent doing one pass. After the agent checks in a second time here, that's when it will spawn sub agents and have it check its work and kind of go in this QA loop that I have built into the system.
11:18But we haven't even done that yet. So that's just the first one shot output. I always like to just have a check-in gate there, but now we can go back to the agent, give our feedback, and then the agent knows to also spawn QA sub agents, and it just goes in a loop from implementation to QA with other agents until finally has something worth bringing to me, and then I'll finally review it.
11:39So this is really just step one there, but for this first output, pretty darn good. So I'm just gonna go back to this agent and riff for a second. K.
11:48Um, first pass is pretty good. There are some things missing though. For example, when I go into linear into the main homepage, if I select the filter, it is, uh, it's like this weird translucent kind of view where you can't actually see some of the stuff.
12:04Like, it gets cut off. Take a look at the screenshot. And then also, when I go when I click into an issue, the the pop up, like, toolbar, I see an emoji for some reason.
12:13That's definitely wrong. You need a I see a bunch of emojis with this pop up toolbar, but you can't even see this. Like, look at this screenshot.
12:19I can you're barely even gonna make this out, but I need you to double check this. This is an important one with the agents because I have a feeling that it's gonna take some work to get that right, but it needs to match Linear's pop up toolbar as closely as possible. Let me just give you Linear's.
12:34It's, uh, I don't even know what you would call this. It's this formatting toolbar. You should match the iconography exactly, and this needs to work.
12:42So you need to test this somehow or have the agents test this in this next QA step. There's other issues too. For example, when I click into an issue, we don't have the ability to add sub issues.
12:53The comment box is not formatted properly. Our comment box is not exactly like Linear's. It's way cleaner of a design, and they have this nice little send button and this attach feature.
13:03That needs to be fixed. And then when I'm in an issue, the properties tab on the left or on the right, when I select priority or assign or labels, that is just again, it's I can't see it.
13:14It's just translucent. Here's here's a screenshot. And then finally, when I hit command k, the command palette, that you can't see it really either.
13:21So stick to these systems. Stick to the skill exactly. Spawn QA agents and do not stop until everything is fixed.
13:29And it took a couple rounds of me just telling the agent, keep going, keep going, keep going, just pushing it along. But, uh, now we've got apparently a faithful recreation of linear, a pixel faithful according to Claude. Let's check it out.
13:43And we'll go back to localhost thirty fifty. Hit refresh. And let's see if some of these changes were made.
13:48Let's check up command palette first. Nice. That's looking pretty similar to linear's.
13:54The iconography is a little bit different, but I like the shading. That's exactly what I wanted. Let's click into an issue here.
14:00Alright. Nice. We have this comment feature now.
14:03Very similar to Linears. We just go into Linears. Just do random test, test, nice little comment feature.
14:10What about sub issues? Sub issues could use a little bit of work. Ours is not exactly styled like theirs, so let's just look at the rest of these.
14:17If we look at the panel on the right, to do. Nice. That's working.
14:20Nice. All of these are working. Set due date next week.
14:24Nice. Label. Add the project.
14:27Boom. That's looking great. Projects, issues, filter.
14:31Filter is now showing up properly. We can select forward list. I'd say we're about 95% of the way there in cloning linear.
14:38But let's just get this thing deployed first because right now it's on local host thirty fifty, and then we can go back and make tweaks if we'd like. So I'll quickly discuss how to do that. This is relatively easy.
14:48I just deploy to Vercel. It's my preferred way to deploy these apps. And what I do is I have just given an agent previously the Vercel API key so it can just access my Vercel right away, and it knows my account, and it just deploys that automatically.
15:02So I don't need to go into the Vercel UI, click around, connect the GitHub repo, anything like that. It just will automatically deploy to Vercel. So that's what I'm gonna tell the agent now.
15:10Okay. Approved. We're good to deploy to Vercel, and it is fully deployed.
15:16So we'll just go in and check on that live link. Open it up in our browser, and boom.
15:21Just like that, we have a live link. We've got a fully functioning linear clone live online. But like I mentioned, the point is not to try to profit off this.
15:29I guess you could, but best of luck. But rather, now that it's ours, we can customize it however we like and even rebuild the stuff that linear makes you pay for. For example, I noticed Linear keeps its insights dashboard.
15:41This thing, insights. They keep this behind a paywall. It seems like a pretty cool feature.
15:45You have all these different people on your team showing how many tasks they have open, in progress, in review. So what we could do is we could just take this, because this is just kind of docs, but we have a screenshot here to reference. And that's probably enough to just give it to an agent.
15:59Copy this, paste it into the agent, and say, okay. Now I wanna build out this feature. And then you can just customize it however you like.
16:05It really is kind of endless. So you can keep customizing, keep adding features however many you'd like, and then when you're in a comfortable spot, the last thing I wanna build, and this is arguably the most important part of this entire thing, and that is giving an agent like Claude access to this app directly. So let me show you what I mean.
16:20If we go back to linear or our linear clone here, I want Claude to be able to do everything that I could in this application. So creating new issues or going into the issue and updating the contents in here or adding comments or changing priorities, statuses, assignees, like literally everything I could in the application.
16:39Because if I'm clicking around UIs, that is just so twenty twenty five. Like, I'm joking, but I'm seriously that lazy now where I don't even wanna press any buttons anymore.
16:47I want the agents to be able to do everything, and the beauty of this app being our own is we can now do exactly that. So let me quickly show you how to build this out and have your agent talk to the app you just built. And to do that, to get our agent to talk to our custom app, we're gonna build out an MCP server.
17:02I And know that sounds complicated. A year and a half ago, this would have been a real project, but now an agent could just do this in basically one shot, especially since our system is already preprogrammed to know how to do this. So if we just go back to our agent in cursor, I can say, now build out the MCP server and the API endpoints.
17:20Follow the directions in our system. Every button should be accessible by an agent with the MCP.
17:28And it's gonna take that, run with it, look at the skill file, look at part b API and MCP to follow the approach. We've got the API endpoints and the MCP server built out. It is connected.
17:39The agent went through the entire MCP config, set this up. So if I go to another agent, like a whole new chat, just go to a new terminal here, open up another Claude session, and I go slash MCP, linear clone is right here.
17:53Boom. Boom. It's connected.
17:54So I can just say create an issue in linear clone for the redesign. Set it to high. Due tomorrow.
18:00And then in like two seconds, it just created an issue. So if we go back to our clone and just hit refresh, boom.
18:07There it is. Just like that. That easy.
18:09So now we've got Claude or any agent with an ability to chat with our application. So now this starts to become a genuinely useful project management tool. And, yeah, I know Linear has an MCP server, but it's also just kinda fun to know that we've built a platform from scratch for us and an agent to access.
18:26Like, we've built an entirely agentic platform in just a few prompts. That to me is really fun. That's much more fun than just using an out of the box software.
18:33Okay. That is how to clone linear in really most of these SaaS applications. I will include the GitHub repo to this linear clone if you wanna just swipe that along with a repo to the full cloning system.
18:44Just copy the URL like I did in the beginning of this video, give it to your agent, and say, follow this system exactly. And would love for people to put the system to the test, see how it does, send me feedback so I can keep making it better. Now, an app your agent can talk to isn't able to do much if the agent itself hasn't been configured properly.
18:59So check out this video next. I'll take you from zero to your first working AI agent in ten minutes. No code, no n eight n, just by talking to it exactly like we just did in this demo.
The Hook
The bait, then the rug-pull.
Linear is a $1.25B product management platform with a design so polished it has become a reference point for the industry. Pat Simmons opened Claude Code on an afternoon and built a working replica. The title is a provocation — but the demo is real.
Named ideas worth stealing.
01:28list
Clone-App-Pat-Pro (8 Steps)
- Recon
- Extraction
- Design.md
- Build
- QA Loop
- Deploy
- Make It Yours
- MCP Server
A repeatable 8-phase pipeline for cloning any SaaS to production-quality with zero manual coding, using Claude Code, the Claude Chrome extension, and Cursor.
Steal forAny internal tool, client project, or SaaS replacement where you want to own the codebase and extend it freely
How they asked for the click.
VERBAL ASK
18:35link
“I will include the GitHub repo to this linear clone if you wanna just swipe that along with a repo to the full cloning system.”
Low-key, no hard pitch; relies on value delivery throughout. Newsletter link in description, next-video tease at outro.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
OTHER LINKSAlso linked in the description.
Visual structure at a glance.
