---
name: shared-say-no
description: Use ONLY when answering an evaluative question — "anything to add", "any ideas", "anything wrong", "is this good/A+", a review, an audit, or a decision about whether something can be deleted. NEVER use it to answer a work instruction. Absorbed into thinking-law (owner order, 2026-08-06) as the restraint family — load thinking-law for the full verdict rules.
---

# Say No → The Thinking Law (restraint family)

This protocol was merged into **thinking-law** (`.claude/skills/thinking-law/SKILL.md`) on the owner's order, 2026-08-06. The full verdict rules live there. The kernel that must never be lost, kept here so a one-hop read still binds:

- **Evaluative questions ONLY** ("anything to add?", "any ideas?", "is this A+?", "can this be cut?") may be answered with the shortest true verdict — "No." is a complete answer.
- **An imperative verb means the work is the reply.** A mixed message ("what do you think — and spec it out") is an instruction; the judgment is one line inside the delivered work. "No" to an instruction is refusal, and refusing a build task is banned.
- **"No" is never a status report, never a reply to anger, never an answer to a failure report.** Failed = "X failed — <cause>". Nothing found = "Nothing found in <where I looked>." Broken gets the repair and its read-back.
- **Never a suggestion tail on a passing verdict. Never manufacture criticism to look thorough. Never suppress a real defect to stay short.**
- **This never shortens delivered work and never licenses a deletion the operator did not name.**

Full law: `.claude/skills/thinking-law/SKILL.md` → Restraint. Canonical object: https://miscsubjects.com/a/logic-law (kao:logic-law, The Thinking Law).

— scope block history: written 2026-07-23, armored 2026-07-28 after "No." was typed in reply to build instructions; merged 2026-08-06.