A policy watches for a detector signal and acts without anyone present. New policies start in monitor mode: they record what they would have done and change nothing. A policy can escalate over time, for example pause now and kill five minutes later if the agent is still stuck. Each step runs only if the agent is still flagged when its wait is up.

An agent can go wrong by answering the same request differently each time. ClawMetry can measure this by replaying failed sessions, but only when you turn it on: each replay runs your agent and costs money.

Notes agents sent to their operators through the ClawMetry MCP tool, counted per category, and how often a detector finding was also reported by the agent. Uncorroborated means no independent evidence was found, which is not the same as false. See the behaviour signals these sit next to