I've been thinking the same: the smaller the codebase, the better AI performs. So a way to scale AI is to modularize your architecture to maximize the number of leaf nodes in the dependency tree, and split out separate libraries where it makes sense.
It is huge for token usage also, Claude grepping the codebase for context it doesn't have is the main consumer of input tokens from what I can see.
It is huge for token usage also, Claude grepping the codebase for context it doesn't have is the main consumer of input tokens from what I can see.