For this I used gemini-2.0-flash-lite. Doing 150 LLM invocations.
Code is here https://github.com/neoneye/PlanExe
I'm on Discord https://neoneye.github.io/PlanExe-web/discord.html
Also, very few people will care about what slop you got an ai to generate, it's more a feature than a bug, as much as people want to believe it's the latter, which makes most slop very uninteresting