I even used AI to code my own harness in C and my own VSCode like IDE in C++ (I hated how slow it felt) and I still used under 1b the months where it did most of the coding.
Just wondering how/what these guys claiming to use a full Claude/Codex 20x subscription are burning it on.
Edit: Also, I never use subagents.
Last week's plan review: 25 yes/no questions about my repo, one agent per question reading the code, the git history and the live site, then one skeptic agent trying to refute each answer with file:line. It overturned seven, including a fix of mine that would have broken the service worker. Nothing was written. Every finding came from reading what already existed, 26 times over.
The rest is waste. One run fanned out to around 70 agents and ate a 5-hour window. Parallelism is capped since.
And it gets back 26 summarized reports.
Then another subagent is reading those summaries without seeing the full code directly and giving it a pass/fail?