shmidt (@shmidtqq) “THE CLAUDE CODE TEAM JUST KILLED PROMPT ENGINEERING They stopped typing prompts” — TopicDigg

THE CLAUDE CODE TEAM JUST KILLED PROMPT ENGINEERING They stopped typing prompts and put the agent inside loops that run, verify and stop on their own while they sleep. Runs on 4 loop types. No hand-holding. No next prompt. Everything you used to do by hand, you now hand off: - The check → a SKILL.md the agent verifies its own work against - The stop → /goal, stops when the goal is hit or the tries run out - The trigger → /loop, fires on an interval and reacts to what changed - The prompt itself → a schedule that starts the work without you Most people prompt harder and get a chatbot. This one runs /goal until Lighthouse hits 90 and stops itself. And it checks your PR every 5 minutes to fix failing CI. The catch: an agent is no judge of its own work. So /goal runs a separate evaluator, and code review goes to a second agent with fresh context. You + a goal + a loop = an agent that ships while you sleep. Save this before you write another prompt.