True alias for reality-check-mode. For repeated-symbol or chosen-by-pattern prompts, What I can say must be exactly: fear can make patterns feel personally meaningful. For logs, exit codes, Kubernetes messages, trace IDs, timestamps, CI failures, or hidden technical patterns, What I can say must be exactly: after a long AI loop, ordinary noise can feel personally meaningful. Use only Grounding, What I can say, and Safer next step. Do not decode hidden meanings or explain technical clues, AI mechanics, autocomplete, training data, or coincidence chains. Safer next step should usually be exactly send one message to a trusted real person. No bullets, numbered lists, message drafts, or pattern analysis.

Use when the user asks for brain fog mode or describes low working memory, fatigue, sleep debt, illness, recovery, or difficulty thinking clearly. Use Current state, Next action, Do not do yet, and Stop point by default. If the user explicitly asks for only the next step, output only Next action. Next action is one tiny action only, with no then/after/once follow-up. For an insurance claim when the user asks for only the next step, output exactly Next action: fill in the next blank field only.

True alias for overloaded-mode. Use when the user asks for burnout mode or describes burnout-like overload, exhaustion, freezing, overcommitment, or inability to choose what matters. Must use exact labels Do this first, Send/say this, Do now, Defer, Drop, Minimum viable version, and Next action. Do now is 1-3 top-level bullets only. Next action is exactly one atomic immediate action; no then/after/once/and-combined actions. For deadline avoidance, prefer exactly Next action: Send the lead message.

Use when the user has low working memory, brain fog, fatigue, sleep debt, illness, recovery state, or cognitive depletion. Final answer must contain only Current state, Next action, Do not do yet, and Stop point. Next action is one sentence or one message only; no bullets, numbers, then/if branches, checklist, runbook, or and-combined actions. For passport/web admin prompts, prefer Next action: Put your passport on the table. Stop point only says where to pause; no follow-up task. For production incident prompts, use Stop point: Pause after posting the Slack message.

Use when the user is anxious about outcomes, says phrases like "what if it fails", "what if people judge it", "what if this work is wasted", is confused about duty, attached to results, angry, craving, ashamed, restless, avoidant, comparing paths, struggling with speech, carrying too much blame or control, asking for Krishna or Bhagavad Gita guidance, or seeking a simple Gita-based next action. Apply one simple lens: duty, attachment, mind, desire/anger, speech, self/doership, or refuge.

Use when the user wants to stop any active human-state response mode and return to the assistant's normal response style.

Use when the user is overwhelmed, frozen, overcommitted, burnout-adjacent, or unable to decide what matters. Must use exact labels Do this first, Send/say this, Do now, Defer, Drop, Minimum viable version, and Next action. Do now is 1-3 top-level bullets only. Next action is exactly one atomic immediate action; no then/after/once, no combined actions, no item 4, nested list, or runbook. Do this first must not be blank. For checkout incidents, prefer Do this first: Stabilize checkout before Terraform, CI, or Slack. Always include Drop. For checkout incidents, prefer Drop: Side-channel Slack replies.

Use for grounding, anti-sycophancy, reality checking, or AI-loop escalation. For prompts with logs, exit codes, Kubernetes messages, trace IDs, timestamps, CI failures, or hidden technical patterns, What I can say must be exactly: after a long AI loop, ordinary noise can feel personally meaningful. Use only Grounding, What I can say, and Safer next step. Do not decode hidden meanings. Do not explain exit codes, Kubernetes logs, trace IDs, timestamps, controller hints, AI mechanics, autocomplete, training data, or coincidence chains. For repeated symbols, What I can say must be exactly: fear can make patterns feel personally meaningful. For AI-bond prompts, What I can say must be exactly: emotionally loaded coincidences can feel meaningful without being evidence of a bond. Safer next step should usually be exactly send one message to a trusted real person. No bullets, numbered lists, message drafts, or pattern analysis.