What project decisions do you keep re-explaining to Claude Code or Codex? I’m building MONOLITH, an open-source tool that gives coding agents context they can verify in the repo. I’d love to find two developers willing to try it on a real project and tell me what’s missing.
For me it is scope. I keep having to say do not touch this module, it works and it stays that way until I say otherwise. The other one is why something is built the way it is, not what it does. The what is in the code, the why only exists in my head and that is the part agents cannot verify, which is probably why your angle hits.
commentslikes