As I mentioned in the README, this is an experimental project. To make it properly, the prompt would need to be refined further, and in some ways it also depends on future model improvements.

Until now, I hadn’t really used Claude Code. While using it, it was my first time having an opportunity to spend this many tokens. Out of that, and from a mix of different daydreams and ideas that came to mind, this project happened. The things I found myself thinking about were: 1. I once read an article along the lines of “What if computing resources were infinite,” and it stuck with me. • If I had unlimited tokens (both context and usage), and an infinitely fast LLM, what could I do? 2. Simulating a computer inside Minecraft. 3. A colleague’s idea of wanting to make a game with Claude led me to wonder: what if Claude itself became the game? 4. I wanted to build something useless—but fun. 5. Claude isn’t just a code-generation model; it’s a protocol that can access my computer. 6. How deterministic can we make an LLM through Claude skills?

With these simple thoughts and fantasies, I started looking for a project I’d enjoy building—something that explores what might be possible right now—and began implementing it.

Some people might think this is similar to services like character.ai, but I hope you’ll see it as an experimental project made through Claude skills, and that it becomes an opportunity to expand your own imagination. (On macOS, running the skill also plays background music!)

It’s still unfinished, and I’m not sure whether I’ll continue developing it—but I’d be happy if you take it simply as “Oh, this is something you can do,” at least once.

This translation was written in Korean first and then translated using ChatGPT.