I think an important caveat is that LLMs are prone to writing unnecessary code, i.e. there's almost a superfluity to it, that at the same time makes it less straightforward and more prone to unnecessary side effects, which it does catch and handle, but that again expands code further.

Then you add an agent that goes through the code and simplifies it. Before every sprint, you get the agent to simplify whatever it can without losing fidelity.

It's really that simple.