Interestingly, this was tackled in this blog post[0] a month ago. They claim that plan files aren't token-efficient, because after reading the plan the workhorse model then reads all the relevant files anyways.
That link just says the planning stage should vet the idea concretely so that the plan focuses on a solution that won’t immediately have to pivot.
And I think plan files should focus on general ideas and invariants, not do “implementation as prose”. That way they perform as mini-ADRs that are useful historically, especially to mine why the system is the way it is.
My plan and implementation files are task specific (so specific workhorse reads only its own slice), and the workhorse itself is spawned from an orchestrator with a very specific small prompt.
I managed even the orchestrator to NOT read the plan whole, at once, but in sections.
The most useful thing is the task ledger the task agent leaves behind, which alongside its structured status message makes a very resilient handoff between all stages.
[0] https://news.ycombinator.com/item?id=48916512