The response protocol for when an agent did something wrong in the real world — stop the agent, assess blast radius, contain (revoke keys, undo changes), communicate to affected parties, write the post-mortem, and add a prevention rule to the responsible skill's Pitfalls. Use when the user says "the agent sent/deleted/bought something it shouldn't have", "kill the agent", "roll this back", "we have an incident", or any agent action caused unintended real-world effects. Don't use for outputs that are merely wrong but caused no harm — that's prompt-debugger.
