I Stopped Using Claude Code as a Giant Prompt and Started Using It as Project Ops

If you use Claude Code on a real project for than one-off coding tasks, you eventually hit the same wall: the model is good at solving the task in front of it, but every new session still has to reconstruct the project. For me, that got especially annoying in a solo-de monorepo. I was not just asking Claude to write code. I was also using it for: backlog triage bug capture planning the next task weekly status summaries preserving decisions across sessions At some point I realized I was trying to solve a workflow problem with a better prompt. That was the wrong move.