diff --git a/plan-ceo-review/SKILL.md.tmpl b/plan-ceo-review/SKILL.md.tmpl
index 7d83703fd..72628bade 100644
--- a/plan-ceo-review/SKILL.md.tmpl
+++ b/plan-ceo-review/SKILL.md.tmpl
@@ -407,7 +407,7 @@ Follow the preamble's session rules; `CONDUCTOR_SESSION: true` changes transport
    wins. When `QUESTION_TUNING: true`, include `<gstack-qid:plan-ceo-review-mode>`.
    These modes differ in kind, not coverage; do NOT score completeness.
 
-4. **Mode handoff:** After selection, before other tools or further questions, run `~/.claude/skills/gstack/bin/gstack-ceo-mode-handoff "<selected mode>" --decisions "<rows or none>"` (add `--auto` for `plan-ceo-review-mode: AUTO_DECIDE`). It prints the matching line below. Then send brief chat beginning with that line: the mode's application and rationale; every governing approved row's ID, answer reference and accepted scope. Keep rows separate.
+4. **Mode handoff:** After selection, before other tools or further questions, run `~/.claude/skills/gstack/bin/gstack-ceo-mode-handoff "<selected mode>" --decisions "<rows or none>"` (add `--auto` for `plan-ceo-review-mode: AUTO_DECIDE`). It prints the matching line below. Then send brief chat beginning with that line, before any other tool call, plan write or section load, and never skip the helper: the mode's application and rationale; every governing approved row's ID, answer reference and accepted scope. Keep rows separate.
 - `plan-ceo-review-mode: AUTO_DECIDE`: `Auto-decided review mode → <selected mode> (your preference). Change with /plan-tune. Approved decisions: <rows or none>. <Application and rationale>.`
 - Other selections: `Mode: <selected mode>; approved decisions: <rows or none>. <Application and rationale>.`
 
diff --git a/test/skill-ceo-section-ordering.test.ts b/test/skill-ceo-section-ordering.test.ts
index 8b6949ffa..31e512378 100644
--- a/test/skill-ceo-section-ordering.test.ts
+++ b/test/skill-ceo-section-ordering.test.ts
@@ -131,6 +131,15 @@ test('CEO handoff carries all answered rows instead of one synthetic approach',
   expect(handoff).not.toContain('<approved 0D approach>');
 });
 
+// ci-37176837432 paid-slice-3 HOLD SCOPE skipped the helper and paraphrased ("holding scope");
+// ci-37198445662 paid-slice-3 HOLD SCOPE ran it, then wrote the plan, loaded sections and probed Codex
+// for 114 s before the posture chat. Both spent the case's 240 s post-selection window.
+test('CEO mode handoff chat follows the helper before any other tool call', () => {
+  const selection = between(skeletonSource(), '### 0E. Mode Selection', '### 0F.');
+  const instruction = selection.slice(selection.indexOf('4. **Mode handoff:**')).split('\n')[0]!;
+  expect(instruction).toContain('Then send brief chat beginning with that line, before any other tool call, plan write or section load, and never skip the helper');
+});
+
 // Guards the public handoff instruction, not model compliance or posture detection.
 test('CEO mode handoff applies the selected mode before the next question', () => {
   const selection = between(skeletonSource(), '### 0E. Mode Selection', '### 0F.');