diff --git a/agents/.agents/skills/claude-subagent-playbook/references/prompt-templates.md b/agents/.agents/skills/claude-subagent-playbook/references/prompt-templates.md
index 604b582..4d0bb04 100644
--- a/agents/.agents/skills/claude-subagent-playbook/references/prompt-templates.md
+++ b/agents/.agents/skills/claude-subagent-playbook/references/prompt-templates.md
@@ -223,7 +223,7 @@ Test command (expect {{N}} passed): {{command}}
 
 Вердикт узкой перепроверки Клода бери прямо из строки task-notification —
 обёртка требует финальным актом только VERDICT-строку; файл перепроверки
-читай лишь при `ISSUES_REMAIN` или споре (эмпирика 2026-07-13: экономит
+читай при `ISSUES_REMAIN`, при `OVERREACH` в той же строке или споре (эмпирика 2026-07-13: экономит
 чтение без потерь).
 
 Кавеат: проверь, что Codex-ревьюер может читать `$SCRATCH` из песочницы
diff --git a/agents/.agents/skills/claude-subagent-playbook/references/prompts/recheck-header.md b/agents/.agents/skills/claude-subagent-playbook/references/prompts/recheck-header.md
index fe1e80f..fb07264 100644
--- a/agents/.agents/skills/claude-subagent-playbook/references/prompts/recheck-header.md
+++ b/agents/.agents/skills/claude-subagent-playbook/references/prompts/recheck-header.md
@@ -5,23 +5,27 @@ 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:
+Judge the repair, not only the closure — the likeliest source of an
+overreaching fix is your own prescription, so put that on trial too.
 
-- 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.
+Before writing NOT_CLOSED, check that a closing state exists at all, and
+price the demand against what it buys: a demand the platform cannot
+satisfy is not a valid NOT_CLOSED, and neither is one whose cost dwarfs
+what it protects. That weighing settles invariants of your own code — it
+does not settle a finding about access, data or money.
 
 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
-spot a NEW defect while re-checking, report it with a new ID in the same
-index format — narrowness limits scope, not honesty.
+REJECTION_VALID | REJECTION_INVALID (why)`. Where the implementer
+reported FIXED, append the verdict on the repair itself:
+`| PROPORTIONATE` or `| OVERREACH (what reached further than the finding
+required)` — OVERREACH is a message upward, not a blocker, and does not
+by itself make the run ISSUES_REMAIN. Judge a rejection by its argument
+in the resolutions report — contract and test, not taste. If you spot a
+NEW defect while re-checking, report it with a new ID in the same index
+format — narrowness limits scope, not honesty.
 
-Final line: RECHECK: ALL_CLOSED | ISSUES_REMAIN
+Final line: RECHECK: ALL_CLOSED | ISSUES_REMAIN — and, if any repair was
+judged OVERREACH, the IDs of those repairs on the same line.
 
 The implementer's resolutions report path, test command and expected
 counters are appended below.