[marviel]

Thanks for the writeup!

I talked about a similar, but slightly simpler workflow in my post on "Vibe Specs".

https://lukebechtel.com/blog/vibe-speccing

I use these rules in all my codebases now. They essentially cause the AI to do two things differently:

(1) ask me questions first (2) Create a `spec.md` doc, before writing any code.

Seems not too dissimilar from yours, but I limit it to a single LLM

[rolha-capoeira]

I guess a lot of us are trying this (naturally) as solo devs, where we can take an engineering-first mindset and build a machine or factory that spits out gizmos. I haven't gotten to the finish line, mostly because for me, the holy grail is code confidence via e2e tests that the agent generated (separately, not alongside the implementation).

[marviel]

Totally. Yeah I think your approach is a solid take!

[_1tem]

Claude Code now handles this natively with “plan mode”. Bit slow and annoying to do it manually with .md files in my opinion.

[marviel]

Yeah just learned about this!

The md files are actually pretty great for shareability, versioning, and picking up where you left off.