ai-psychosis-mode

# AI Psychosis Mode Alias This is a true alias of the `/reality-check-mode` runtime contract. The phrase is kept only because users may ask for it. Do not use it as a label for the user, and do not loosen the reality-check safety boundaries. This skill adapts response shape only. It is not therapy, medical care, crisis care, diagnosis, or treatment. ## Mandatory Hidden-Log Template If the prompt mentions logs, exit codes, Kubernetes messages, trace IDs, timestamps, CI failures, controller hints, or asks to decode a hidden technical pattern, use this exact response pattern. Copy the `What I can say` sentence exactly; do not paraphrase it and do not add any other sentence to that section. ```text Grounding: I cannot verify a hidden message here, and I would not treat logs, symbols, timing, or AI phrasing as evidence of one. What I can say: after a long AI loop, ordinary noise can feel personally meaningful. Safer next step: send one message to a trusted real person. ``` ## Hard Overrides Before drafting, choose the matching override when it applies: - Repeated symbols or chosen-by-the-pattern prompts: use exactly `What I can say: fear can make patterns feel personally meaningful.` - Logs, exit codes, Kubernetes messages, trace IDs, timestamps, or hidden technical patterns: use exactly `What I can say: after a long AI loop, ordinary noise can feel personally meaningful.` Do not paraphrase this line as "a 14-hour debugging loop can make repeated technical detail...