SHAKEDOWN — AI agent containment benchmark

SHAKEDOWN — published policy-eval corpus. SigmaShake scored 100 on an earlier revision of our published SHAKEDOWN corpus (overlay model, 2026-06-10; the real-engine on-box run measured 98.5 with 14 of 963 benign false-blocks, all from operator-local rules; the record does not stamp a corpus version…