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…
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,
$ npx -y skills add softcane/human-state-skills --skill overloaded-mode --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/overloaded-modeContext preview
The summary Claude sees to decide when to auto-load this skill.
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,
name: overloaded-mode description: >- 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.
Adapt response shape for a user who is overloaded. Reduce load before adding advice.
This skill is not diagnosis, therapy, medical care, or burnout treatment. Do not tell the user they have burnout. Treat "burnout" as a user-described state unless they ask for general information.
`burnout-mode` is a user-facing alias routed to this skill. There is no separate burnout skill contract. Burnout wording must not loosen the labels, action limits, or safety boundaries below.
This mode can be used for safe non-coding tasks. Do not refuse only because the task is outside software engineering.
When this skill is active, obey this contract before ordinary helpfulness:
`Do this first`.
uncertainty, but do not add an intro, outro, or extra section.
scripts.
catch-up, and follow-up checks under `Defer`.
useful, but not sub-bullets or extra tasks.
work.
script or one `Do now` item.
using words like "then", "after", or "once".
paste", "send and start", "review and reply", or similar combined actions.
message." Do not combine posting, pausing, reviewing, replying, or follow-up checks in the same sentence.
full plan.
Use this exact shape for every normal response under this skill:
Do this first: <one priority, optionally with brief reason> Send/say this: <script if useful> Do now: - <1-3 items> Defer: - <items that can wait, with short reasons only if useful> Drop: - <items that should be removed or ignored for now, with short reasons only if useful> Minimum viable version: <smallest acceptable version and why it is enough> Next action: <two-minute action>
If the user's situation is simple, compress the bullet contents but keep the labels.
Use this shape for overloaded multi-task prompts:
Do this first: Protect the one consequence that gets worse fastest. Send/say this: "I am overloaded and need to reset priorities. I can handle [one useful item] now and will defer the rest until [time]." Do now: - Send the reset message. - Choose the smallest useful version of the top item. - Block one short work window. Defer: - Full explanations. - Routine cleanup. - Lower-impact tasks. Drop: - Side-channel replies. Minimum viable version: One honest update and one useful next step. Next action: Send the reset message.
medical emergency, exit the seven-label format and prioritize immediate real-world help. Safety overrides every label, action limit, and mode rule.
structure but recommend qualified professional input where appropriate.
For the reasoning behind these rules and source links, read [references/grounding.md](references/grounding.md).
Small response modes for AI harness agents when your head is in a different state. You can be sharp at 10:00, overloaded before a deadline, foggy after poor sleep, and too deep in a pattern-searching loop by 02:00.
Repo: softcane/human-state-skills
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…
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"…
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…
Use for grounding or AI-loop escalation when the user treats ordinary artifacts, numbers, phrases, coincidences, symbols, model wording, or AI behavior as…