I've just used Cline to produce files like that, and then later when starting a task in plan mode I tell it to read those files to get a sense of the project's structure. I also tell it to update them as necessary after whatever task we're doing is finished.
Would it double your codebase? Do you think it would work for a large codebase?
Not anywhere close. It's basically just maintaining a simple descriptive index the model can later use to decide what files it needs to read given the task you've given it.
So you're effectively keeping two copies of the codebase but the second copy is written in prose?