i stopped paying for 90% of my subscriptions


I’ve cut out 90% of my software subscriptions.

But I didn’t stop using a single one of those tools, because I rebuilt them.

And whenever I have to enter my credit card for a subscription, I think twice.

And you should be doing the same.

So why isn’t everyone doing it? Because they start with the wrong build.

See, most people’s first project is usually a tutorial clone…

  • They follow the tutorial’s instructions
  • They finish a working copy of someone else’s app
  • And they never open it again because it never solved a problem they had

But if you go with a tool you already pay for, you won’t have any of these issues. Because you’re already using it every day.

And it’s easier to build than you might think.

So here are the 6 moves to turn your subscriptions into software you own.

1. Start with what you already pay for

Open your subscriptions and pick the one you use most and understand best.

That should be your first build.

Mine was a task app. I was paying like $30 for an app called “Things 3,” so I built my own version (and that’s the one I now use).

2. Reverse prompt to find the rest

Once your first build is done, don’t sit there trying to think up the next 5.

Instead, just ask Claude Code.

You can say something along the lines of: “Hey, based on what you know about me and the tools I use on my computer, what should we build into a mission control?”

It’ll give you a ton of ideas you’d never write down yourself.

3. Screenshot the tool and hand it over to Claude

I know how crazy that sounds, but this is the entire build step.

You just need to:

  1. Take screenshots of the app you’re replacing
  2. Hand them to Claude Code
  3. And say “hey, build this for me”

I find that when I give Claude Code screenshots and a link to the original, it builds it out really quickly.

Screenshots beat a description because you’re handing over finished decisions instead of describing them.

Now you don’t want to leave everything you build as separate little apps…

4. Put them all into one dashboard

I call this dashboard a mission control.

To give you an idea, here’s everything inside mine:

  • My newsletter studio
  • My task board
  • My content capture board

And that does 2 things for you:

It gives you every tool you need in one place, and it takes those subscriptions off your card.

5. Host it so it’s available on your phone

Once a tool works, put it on something like Vercel.

In case you haven’t come across Vercel, it’s a cheap hosting site that takes minutes to set up.

That way, your mission control is on your phone, your tablet, and any other device you’ve got.

Mine is hosted there right now, and I check it way more often because I can pull it up from anywhere in the world.

6. Let it propose its own next feature

Now stop telling Claude Code what to build.

At this point it knows what’s in there better than you do, so it’ll spot things you’d never think to ask for.

Here’s a prompt I used on my build:

“Take a look at the mission control we’ve built, the features and the purpose of the application, then come up with 5 ideas for how we could improve this application where it brings us closer to the goals of the app and improve our lives.”

So as you can see, I’m not giving Claude Code commands on what to do.

I’m just saying, hey, explore the app and figure out what to do.

When Claude’s answer came back, it said my homepage was a static grid of tool cards. In other words, my homepage was showing off the app instead of running my day.

So it suggested turning the homepage into a live daily brief instead.

I liked that idea, so we ran with it. Then I asked what else we could add, and I kept pulling on that strand.

So remember…

The first real app you ship shouldn’t be a tutorial clone. It should be the thing you’re currently paying for.

And if you’re looking at your card statement right now with no idea which one to start with, you don’t have to work that out on your own.

Every Friday I run a live session inside the Vibe Coding Academy where 860+ members are shipping their own apps. Come build your first one with us.

Join the Vibe Coding Academy here.

Keep shipping,

Alex

Ship/It Weekly

The weekly newsletter for founders and builders using AI to ship faster—practical tactics, tools, and real-world lessons from Alex Finn.

Read more from Ship/It Weekly

There's a whole genre of AI videos I can't stand… The ones where the creator tells you to set up an army of 50 sub agents, drops a GitHub repo underneath it, and calls it a starter kit. I hate them because they always end the same way... You open it You can't work out what any of the 50 agents do You end up running none Or you run them all, and it cripples your performance and skyrockets your costs It might feel really tempting to use all 50 agents. It might feel like you all of a sudden are...

6.44 billion people have never used AI. Yes... not once. Even though the most powerful technology ever created is free to try, most people have never touched it. Which is why everyone using AI to build and automate their lives has an OBSCENE advantage right now. To help you stay on the cutting edge, I've put out 3 posts over the last couple of weeks. 1. 77.6% of Earth has never used AI In a decade 75% of this chart will be red. Until then you have the greatest arbitrage opportunity there is....

I have never designed anything in my life. I'm very unartistic, and I just stink at all of that. So when I started using Claude Design, I experimented a ton just to figure out what I even liked… I asked questions I tried things 10 different times And I hit my limits fast without creating anything good Ever had a similar situation? Chances are, you made the exact same mistake I did… You opened the best AI tool before you knew what you wanted. But, as you probably already know, every AI tool...