This changes everything (not clickbait)


Hey Reader,

I need to tell you something.

For the last 2+ weeks, I went all-in on Claude Code and Codex.

Zero Cursor. Cold turkey.

I even documented it publicly on Twitter.

Then yesterday happened.

Cursor Stole Everything

I'm running Cursor's developer version (not public yet).

And I almost spit out my coffee when I saw the new settings.

Full support for Claude Code and Codex agent skills.

There's even support for Claude Commands and Plugins.

It's like they looked at everything that made Claude Code special... and said "we'll take all of it, thanks."

But Here's What Really Matters

Forget the features for a second.

Imagine this:

You're in Cursor. You tell it: "Use Claude Code to implement this."

Behind the scenes, Cursor understands Claude Code is an external tool.

It knows how to call it. It sends the task over, gets the result back, and returns it to you.

Think: one manager delegating to multiple specialists.

Cursor handles the thinking. Claude Code does the heavy lifting.

You get the result without burning through your Cursor subscription.

That's what Cursor is really building without telling anyone.

I've seen it live in action this morning and I couldn't be more excited.

Why You Should Care

This signals that Cursor understood something very important.

They cannot compete on token cost, and they never will be.

So what's the next best thing? Join them, instead of fighting them.

Let's be honest, the $20/$60 plans of Cursor are pretty much useless.

The $200 Ultra plan is alright, but I've had months coming close to $500.

Now imagine you just had a $60-200 Cursor plan that was truly unlimited.

Sounds good, right? Well, that's essentially what we're getting here.

The Future of Subscriptions

In the near future, you will be able to Cursor to orchestrate other tools.

You might pay $60 for Cursor, $100 for Claude Max, and $20 for ChatGPT.

And those $180 a month would get you thousands of dollars worth of tokens.

Think of it like this...

Use Cursor for orchestration, debugging, browser, plan mode, etc.

Use Claude Code for the heavy lifting, burning through Opus 4.5 tokens.

And if you really want to, you could use Codex… but that feels optional.

The Honest Truth

I tested it. It works.

Can't share more details because, well, Cursor hasn't published it yet.

But when this goes public, expect a lot of people to suddenly say "Cursor is fixed now"... 😂

All I can say is that this is not only more affordable, but also more powerful than Cursor on its own.

I keep testing Cursor with Claude Code and report back with updates.

Talk soon,
Rob

P.S. You didn't hear this from me, but... I might soon close the AI Builder's Blueprint forever to focus on my Inner Circle. But you can secure $100 OFF today before midnight → Start Building Today (only hours left)

Robin Ebers

Coder of 20+ years teaching non-technical people how to build their own software business in 30 days with AI. No devs or code required.

Read more from Robin Ebers

Hey Reader I've never told anyone this story. And if you think you're "too old" or "not technical enough"... This one's for you. Here's a confession: I haven't written a single line of code in 11 months. Not one. And yet I build apps every single day. Let me explain. The Backstory I started learning to code when I was 13. Windows 95. C++ and Pascal (dinosaur languages today). For 20 years I loved it. Made good money. Built a career. Then I started watching kids do in 2 hours what took me a...

Hey Reader, You know why building with AI feels so damn hard? It's not because you're not technical enough. It's not because the tools are too complicated. It's because everything changes every 48 hours. A new model drops. New tool launches. Someone on Twitter says Cursor is dead. Someone else says Claude Code is the future. Then Antigravity does something. Then Codex gets an update. And you're sitting there thinking... "What the hell am I supposed to use?" I Just Proved This (The Hard Way)...

Reader, I did something crazy this week. I built a macOS app from scratch. Doesn't sound that wild until I tell you: I've never built a macOS app before. I've never written a single line of Swift (that's Apple's programming language). I've never even touched an Apple developer account. And yet… 79 minutes later, it was done. This is NoteMac, a text editor for Mac (because I was tired of the included one). It's not "sorta working", it's actually... done. Shipped. This reminded me of one of my...