habitlisted

# memory-loop: habit HABITS.md (default `~/.claude/groundwork/HABITS.md`, created by the `setup` skill) is the frame where lessons become standing behavior. If the file is missing, tell the user to run `/memory-loop:setup` (step 2) first. ## Classify first — the damage question Ask: *"If this behavior fails, does damage remain?"* — production data or infrastructure, outbound messages (chat, PRs, mail), secrets, long-term memory, safety hooks, destructive commands, release/operations decisions. Damage that is later repaired but already happened (costs incurred, a wrong external post, polluted memory) counts as YES. - **YES → 🛑 Hard line.** Write it as a strong prohibition ("Never X before Y"). The blank left by a prohibition *is* the safety margin. - **NO → 🟢 Practice.** Write it positively — "when X, the best move is Y" — in HABITS.md, and put the origin in `HABITS-CASES.md` as a new `## Cnn` section, leaving a `[Cnn]` pointer on the rule. A positive rule points at the action to take; a bare "don't" leaves the next moment empty. - **Ambiguous → 🛑.** Expression defaults to positive; the safety verdict defaults to conservative. These are different axes — warm form, strict verdict. Context can flip the grade: the same verification shortcut that is 🟢 during read-only exploration becomes 🛑 the moment its output feeds an external post, a PR, long-term memory, or a destructive change. Judge by *where the output goes*, not by the action alone. ## Two files: rul