alt Hacker NewsIsn't there a lot of overlap between PLAN, PHASES and DECISION that pollutes the context ? Whereas a simple PLAN.MD to put the harness on track and an ARCHITECTURE as a single source of truth to prevent it go offtrack would suffice and gives it more space for higher level of reasoning ?
These files came to be after I've seen Deepseek create them for itself to track progress.
Then I turned what Deepseek did into an upfront policy.
This seems to work quite well generally: watch the agent as it works, and think what could be provided to make its life as easy as possible