That must be a remarkable model. Smart enough to flawlessly discover everything on its own in every session... but also it just straight up just doesn't obey direction.
Hmmm.
I didn't say give no direction.
I'm saying a lot of devs/engineers little rain dances aren't really bringing the rain.
Keep a basic CLAUDE.md/AGENTS.md that keeps high level details. Have a way to reference other projects/apps/codebases to use as reference architecture.
Don't keep tons of markdown files. Don't keep "decision" documents (these are probably the worst). Don't make skills for every little thing (superpowers are dead these days, stop using them). Oh yeah, don't have the LLM generate docs for reference later... if it can generate the docs it doesn't really need them.
On one project, we decided we didn't need mobile compatibility. That simplified things greatly.
You're going to want to document that somewhere. And if you also have a stakeholder register, you can link the decision to the person who made it.