Agent Scrum: A sprint methodology for continuous software development by AI agent teams, with observations from 324 sprints

Agent Scrum keeps Scrum's core devices (a time-boxed sprint, a committed sprint backlog, story points, velocity, a Definition of Done and a retrospective) and rescales them for teams of AI coding agents. Sprints last two hours instead of two weeks; capacity comes from model rate limits instead of headcount; cost is measured as token velocity, the tokens consumed per merged story point. In the reference implementation, 79% of committed stories reached done inside the sprint (297 of 375 over 90 sprints), ceremony took under five minutes per sprint, and the human stakeholder spent under two hours a day. Working paper, version 0.1.