READY qualifies agents on oversight cost, not benchmark accuracy.

READY argues an agent can score well and still be undeployable, because the real question is whether it hits a reliability target under acceptable human oversight at tolerable cost. In a clinical-audit study across 16 agent systems and 750 cases, two systems separated by 0.3 points of autonomous accuracy (72.8% against 73.1%) diverged sharply once oversight burden was priced in. The testbed is open and runs on existing agent-evaluation infrastructure.