If you use these models on real projects, when has a spec improved the outcome? When has it added overhead? Have you shifted toward shorter briefs, tests, or iterative feedback?
Astra, Fable, Opus 5.0 are better with less instructions. Some of the context has been moved into the harness itself, so things like CLAUDE.md etc are becoming obsolete, and same with PRDs.
These days it's more about saying why than what. ADRs and GDDs would be helpful.
Frontier models are great at filling gaps, and that's the problem, they decide on your behalf.
The plan mostly exists to close those decision gaps. It also helps review: teammates can push back on a 30-line plan in five minutes, but a 2k-line diff takes an afternoon.
Doing it all manually better guarantees quality of course, so makes sense for a lot of problems. But if you're looking to move a bit faster with a bit more risk, I'd sacrifice the writing step without sacrificing the reading & validating step.