See what is being checked. Decide what happens next.
These settings apply to all runtimes on this node. Checks find evidence; they do not block an action on their own.
Approvals ask for a decision. Findings explain what a check noticed.
Keep watching, notify someone, ask for approval, or take an automatic action.
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.
Review automatic responses and agent reports. For permission decisions and delivered notifications, open their history.
MCP servers, skills, plugins, instruction files and hook files that Claude Code, Codex, Cursor, Gemini CLI, opencode and OpenClaw read on this machine, for all runtimes together. When one is added or changed, the running sessions that load it are flagged. ClawMetry only reads these files and never starts a component, so an MCP server's tool descriptions are not checked.
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