Subagents are super context hungry though. I always hit usage limit when use them in Claude Code. My approach is to break down the plan into tasks and let a single agent work on them simultaneously and create stacked PR. If the tasks can be done in parallel, I spin up multiple sessions in separate worktrees
Maybe you’ve talked about this somewhere but do you work in a team setting or solo?
- how to you generate tasks for input, and roughly how much of your time is spent on that
- do you have a team for reviewing PRs or all just auto merge
- also if you have a team how do you document and comprehend this volume of work (and at what level of granularity)
Subagents are super context hungry though. I always hit usage limit when use them in Claude Code. My approach is to break down the plan into tasks and let a single agent work on them simultaneously and create stacked PR. If the tasks can be done in parallel, I spin up multiple sessions in separate worktrees
How much of the code do you review yourself? And do you still keep track of all the low level details in the code?