Enforce risk-based alignment for AI Agents. Stop Claude/Cursor from guessing on vague or high-impact tasks. Make AI align first, then act: introduce risk classification and clarification mechanisms for Agents, rejecting blind guesses and ensuring safe, controllable development.
1 file for Cursor: cursorrules — 947 tokens loaded in every session.
.cursorrules A 947 tok These files are DmiyDing/clarify-first's own configuration — they tell Cursor how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.