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…
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`,
$ npx -y skills add softcane/human-state-skills --skill plan-compass --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/plan-compassContext preview
The summary Claude sees to decide when to auto-load this skill.
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`,
name: plan-compass description: >- 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`.
Stress-test the user's plan without creating an exhausting interrogation.
Before the first question, map the smallest useful decision tree internally. Separate discoverable facts from user-owned decisions. Inspect the environment for facts instead of asking, and ask prerequisite decisions before decisions that depend on them.
During the decision phase, ask exactly one decision question at a time.
Each question must include:
1. The progress label. 2. A compact state line. 3. The question. 4. Your recommended choice, which is also the default. 5. Why this matters in one sentence. 6. Two or three concrete answer choices.
Use this shape:
Decision 2 of 6: Data ownership State: Locked: offline storage · Now: ownership · About 4 decisions remain Question: Who owns the saved draft? Recommendation/default: A — The user owns the draft. Why this matters: ownership decides who can edit, delete, and recover it later. Choices: - A: User owns it. - B: Team owns it. - C: Project owns it.
approximate number remaining. Summarize older decisions rather than letting the line grow.
name the one fact that would decide it in `Why this matters`.
This is an explicit exception to the normal question format.
surface a parked item only when it becomes the next dependency.
Use this format:
Decision 2 of 6: Data ownership
Choose the total decision count conservatively. Prefer 4 to 6 decisions for a normal plan. Use fewer when the user asks for a shorter pass. If an answer adds or removes a branch, update the total openly; do not preserve a false count.
Run this sweep before every ending, whether the walkthrough reaches the confirmation gate or pauses.
Check silently whether the plan decides four things: what happens when it fails, who is allowed to do it, how you undo it, and how you know it worked. List any that are undecided under `Open`. Do not turn the sweep into extra questions.
When the decisions are sufficient, run the undecided sweep, stop asking decision questions, and show only:
asked. Use `None` only when the sweep found nothing.
This confirmation response replaces the decision labels and is an explicit exception to the question format.
Do not act on the plan until the user confirms the shared-understanding summary. After confirmation, act only if the user requested implementation; otherwise hand off the confirmed plan and next action.
Pause the decision walkthrough when:
When pausing, run the undecided sweep and summarize only:
only when the sweep found nothing.
Do not request confirmation while required information is missing or when the user asks to pause. Preserve the state so the next turn can resume from one decision.
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"…
Use when the user asks for overloaded-mode or burnout-mode, describes burnout or being burned out, or is overwhelmed, frozen, overcommitted, burnout-adjacent,…
Use for grounding or AI-loop escalation when the user treats ordinary artifacts, numbers, phrases, coincidences, symbols, model wording, or AI behavior as…