Injects a learned cognitive fingerprint into Claude sessions and lets agents consult you at decision points. The server loads your Phaedo profile (sample included, real one synced from their app via pairing) and provides two operations: style injection fires automatically at session start, and consultation requests return proceed/clarify/escalate/decline signals when an agent hits a judgment call, gated by user-authored deference policies. Everything runs locally over stdio with encrypted on-device storage. Reach for this if you want agents to mirror your communication patterns and decision-making style without rehashing context every time, or to audit agentic choices against a calibrated model of how you'd actually respond.