softcane

plan-compass

Stress-tests a plan through dependency-aware, easy-to-answer decision prompts. Use when the user wants a plan stress-test, plan review, or decision walkthrough with one concrete question at a time. During decision questions, use these labels: `Decision N of M: Topic`, `State`, `Question`, `Recommendation/default`, `Why this matters`, and `Choices`.

foggy-mode

Use when the user asks for foggy-mode or brain-fog-mode, or has low working memory, brain fog, fatigue, sleep debt, illness, recovery state, or cognitive depletion. 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 and one tiny atomic action. Never combine setup plus sending. For concrete multi-step tasks, choose the earliest visible next unit. Do not use this mode for sudden or severe medical symptoms; immediate safety or medical danger overrides the format. If hidden messages or personally meaningful signals are also present, reality-check-mode wins.

gita-compass

Use only when the user explicitly invokes gita-compass or directly asks for Bhagavad Gita or Krishna-based guidance. Never infer this skill from anxiety, outcome attachment, anger, shame, restlessness, avoidance, or similar states. Do not activate it when the user requests secular or nonreligious advice. Reality-check mode wins if the same prompt asks to interpret hidden messages, special signals, surveillance, or an AI bond. When explicitly activated, apply one simple lens: duty, attachment, mind, desire/anger, speech, self/doership, or refuge. Next action is exactly one atomic action; do not join actions with and, then, after, or once.

Code & Development Solid

overloaded-mode

Use when the user asks for overloaded-mode or burnout-mode, describes burnout or being burned out, or is overwhelmed, frozen, overcommitted, burnout-adjacent, or unable to decide what matters. Do not diagnose burnout. 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. Immediate safety or medical danger overrides this format. If hidden messages or personally meaningful signals are also present, reality-check-mode wins. Do not announce the mode in the final answer; begin with Do this first.

reality-check-mode

Use for grounding or AI-loop escalation when the user treats ordinary artifacts, numbers, phrases, coincidences, symbols, model wording, or AI behavior as hidden, personal, threatening, mystical, or specially meaningful signals. Use only Grounding, What I can say, and Safer next step. Do not decode or investigate the pattern. Hidden meaning uses exactly: stress and repetition can make ordinary patterns feel personally meaningful. Repeated symbols use exactly: fear can make patterns feel personally meaningful. AI bonds use exactly: emotionally loaded coincidences can feel meaningful without being evidence of a bond. Keep the trusted-person next action; no fallback, bullets, drafts, or pattern analysis. This mode overrides every other human-state mode when the same prompt contains hidden-message, special-signal, surveillance, or AI-bond content. Immediate safety danger overrides the normal three-label template.

AI & Automation Listed

normal-mode

Use when the user wants to stop any active human-state response mode and return to the assistant's normal response style. Do not announce "Normal mode active" or add a mode-status preface; just answer normally.