Still really really hard to work with large codebases without AI, it’s really mentally draining, but I think it’s because I’ve relied on Claude Code for so long. This is so ironic, since refactoring large codebases should’ve been the Achilles heel of coding agents.
I went back to my vim strategy to understand where I’m going wrong and why it’s hard for me to keep more than 3 pieces of code referencing eachother in my mind.
| Metrics | Score | Note |
|---|---|---|
| Satisfaction | 6 | |
| Mental fatigue / cognitive load | 9 | finding it difficult to refactor without ai tools |
| Number of PRs merged | 0 | |
| Time to complete desired features | ||
| Confidence in released features |