agents like to read a lot to gather context before and after working, so optimizing for reading makes a big difference! if you're building agents, i highly recommend reading this (or giving it to your agent and ask it to implement the findings) https://x.com/ericzakariasson/status/210…

Cursor@cursor_aiSep 23

We've reduced token costs in Cursor by 7% with no drop in agent quality. Savings came from tighter prompts, selective tool loading, better caching, and compressed file reads.