Forget about Prompt Engineering and tell the agent what to do in the dumbest way you can think of.
At one point we tried “improving” the prompt with Claude’s help. It ballooned to 1,500 words. The agent immediately got slower and dumber. We went back to 103 words and it was back on track.
https://github.com/repomirrorhq/repomirror/blob/main/repomirror.md
At one point we tried “improving” the prompt with Claude’s help. It ballooned to 1,500 words. The agent immediately got slower and dumber. We went back to 103 words and it was back on track.
https://github.com/repomirrorhq/repomirror/blob/main/repomirror.md