Autonomous Vision Monitor (Claude)

Problem: Continuous monitoring either needs a human watching or brittle threshold rules that miss judgment calls.

A domain-agnostic monitoring agent that runs entirely on its own: on a schedule it captures an image, pulls in supporting context (weather, sensor readings, recent history), and has Claude assess the scene against a per-domain rubric using vision, then logs the assessment and alerts a human only when action is actually needed. The architecture is a reusable kernel plus swappable domain packs, so the same agent monitors a garden or a fleet of services with no code change, just a new rubric. It runs headless (no server, no daemon) on cheap edge hardware.