my favorite way to use Claude Code to build large features is spec based
start with a minimal spec or prompt and ask Claude to interview you using the AskUserQuestionTool
then make a new session to execute the spec
@davidhariri you frontload most of the review work in a sense by using an "/interview" command when spec'ing
and then define what tests would result in success/failure of your outcome. and let it free.
i dont understand these 10 agent people tho, can only do ~2 to get the quality i want