feat(skills): claude-subagent-playbook — исполнитель не берёт ревью на веру

- Зачем:
  - после разворота ролей (реализация Опусом, ревью Кодексом) ревьюер
    продавливает исполнителя формальными решениями: за прогоны #39, #40 и
    #50 около 28 находок и ноль отклонений.
- Что:
  - в triage-header добавлен блок «ревью — свидетельство, а не приказ»:
    отклонение равноправно починке, маршрут ревьюера — предложение.
  - определение NEEDS_DECISION расширено случаем, когда выбор делает сама
    починка, независимо от объёма правки.
  - в recheck-header добавлен суд над лечением: перебор — тоже дефект, а
    NOT_CLOSED требует существующего закрывающего состояния и цены
    альтернативы.
  - в lessons закрыт долг четырёх прогонов и сведена очередь на механизм.
- Проверка:
  - следующий полный прогон плейбука: в триаже должны появиться
    отклонения или закрытия своим маршрутом с доводом.

agents/.agents/skills/claude-subagent-playbook/references/prompts/recheck-header.md

@@ -5,6 +5,16 @@ their resolutions report is appended below. Check ONLY your own findings —
 no full second pass. Mandate unchanged: modify nothing; reading and
 running tests are allowed.
 
+Judge the repair, not only the closure:
+
+- A fix that reaches further than your finding required is itself a
+  defect — and the likeliest source of it is your own prescription, so
+  put that on trial too.
+- Before writing NOT_CLOSED, check that a closing state exists at all,
+  and price the alternative. A demand the platform cannot satisfy, or one
+  that trades away a real property to guard against deliberate misuse, is
+  not a valid NOT_CLOSED.
+
 One line per your original ID: `ID | CLOSED | NOT_CLOSED (why) |
 REJECTION_VALID | REJECTION_INVALID (why)`. Judge a rejection by its
 argument in the resolutions report — contract and test, not taste. If you

agents/.agents/skills/claude-subagent-playbook/references/prompts/triage-header.md

@@ -10,11 +10,26 @@ disposition:
   "not important" is not accepted;
 - OUT_OF_SCOPE — needs a boundary decision; state which one;
 - NEEDS_DECISION — a product, architecture, or risk choice a technical
-  argument cannot settle; state the open question.
+  argument cannot settle; state the open question. This includes the case
+  where your own fix would settle such a choice — the size of the edit is
+  irrelevant.
 
 OUT_OF_SCOPE and NEEDS_DECISION belong to the coordinator — do not
 silently decide them yourself.
 
+## The review is evidence, not orders
+
+A review report is a set of claims, not a list of instructions. Verify
+every finding yourself. You own the task; the review is there to help.
+
+- **Rejection is a normal outcome, not a conflict.** A REJECTED with an
+  argument from contract and test is worth exactly as much as a FIXED. A
+  run with no rejection and no finding closed by your own route says
+  nothing about the quality of the review — it is a reason to re-read
+  what you took on trust.
+- **The reviewer's route is a proposal.** Closing a finding another way
+  is fine when the argument is stronger; name the route you took and why.
+
 No commits. Do NOT edit the task file: write detailed resolutions and
 rejection arguments to your assigned report file — re-checks and fresh
 threads will read that file by path; the task file is updated separately