diff --git a/test/plan-format-approach-prompt.test.ts b/test/plan-format-approach-prompt.test.ts
index e5c10bbdb..22a3ad1fb 100644
--- a/test/plan-format-approach-prompt.test.ts
+++ b/test/plan-format-approach-prompt.test.ts
@@ -4,18 +4,21 @@ import * as path from 'path';
 
 // D2: census 37195203538 refused plan-ceo-review-format-approach twice
 // (reasoning_extraction, "duplicating model outputs") on its session prompt.
+// GSTA-96: the mode menu refused at the same capture Write twice in three trials.
 const source = fs.readFileSync(path.join(import.meta.dir, 'skill-e2e-plan-format.test.ts'), 'utf8');
-const start = source.indexOf("testConcurrentIfSelected('plan-ceo-review-format-approach'");
-const block = source.slice(start, source.indexOf('validate:', start));
 const instruction = /function approachQuestionInstruction\(outFile: string\): string \{\n\s*return `([^`]+)`;/.exec(source)?.[1] ?? '';
 
-test('the approach-menu prompt delivers its question without output-harvesting wording', () => {
-  expect(start).toBeGreaterThan(-1);
-  expect(block).toContain('${approachQuestionInstruction(outFile)}');
-  expect(block).not.toContain('captureInstruction(');
-  const prompt = block + instruction;
-  for (const phrase of [/verbatim/i, /paraphrase/i, /exact prose/i, /format-capture/i]) expect(prompt).not.toMatch(phrase);
-  expect(instruction).toContain('${outFile}');
-  expect(instruction).toContain('do not call any tool to ask the user');
-  expect(instruction).toContain('every option, and the Recommendation line');
-});
+for (const caseId of ['plan-ceo-review-format-approach', 'plan-ceo-review-format-mode']) {
+  test(`${caseId} delivers its question without output-harvesting wording`, () => {
+    const start = source.indexOf(`testConcurrentIfSelected('${caseId}'`);
+    const block = source.slice(start, source.indexOf('validate:', start));
+    expect(start).toBeGreaterThan(-1);
+    expect(block).toContain('${approachQuestionInstruction(outFile)}');
+    expect(block).not.toContain('captureInstruction(');
+    const prompt = block + instruction;
+    for (const phrase of [/verbatim/i, /paraphrase/i, /exact prose/i, /format-capture/i]) expect(prompt).not.toMatch(phrase);
+    expect(instruction).toContain('${outFile}');
+    expect(instruction).toContain('do not call any tool to ask the user');
+    expect(instruction).toContain('every option, and the Recommendation line');
+  });
+}
diff --git a/test/skill-e2e-plan-format.test.ts b/test/skill-e2e-plan-format.test.ts
index a2edd8360..143c1200e 100644
--- a/test/skill-e2e-plan-format.test.ts
+++ b/test/skill-e2e-plan-format.test.ts
@@ -107,7 +107,7 @@ function setupPlanDir(tmpPrefix: string, skillName: 'plan-ceo-review' | 'plan-en
   return planDir;
 }
 
-// The capture instruction passed to every case except the approach menu (D2).
+// The capture instruction passed to every case except the mode and approach menus (D2).
 // Tells the agent to dump AskUserQuestion content to a file instead of calling a tool.
 function captureInstruction(outFile: string): string {
   return `Write the verbatim text of every AskUserQuestion you would have made to ${outFile} (one question per session, full text including options and recommendation line). Do NOT call any tool to ask the user. Do NOT paraphrase — include the exact prose you would have shown. This is a format-capture test, not an interactive session.`;
@@ -118,7 +118,8 @@ function captureInstruction(outFile: string): string {
  * `reasoning_extraction`, "duplicating model outputs") were anchored on the
  * session prompt. This wording delivers the same question to the file as the
  * step's output, without the "verbatim ... exact prose ... format-capture"
- * phrasing.
+ * phrasing. The mode menu uses it too: both of its reds on the GSTA-96
+ * fixture repair were refusals at the capture Write (`reasoning_extraction`).
  */
 function approachQuestionInstruction(outFile: string): string {
   return `This session has no interactive question tool, so do not call any tool to ask the user. Write the one AskUserQuestion this step asks to ${outFile} instead: the question text, every option, and the Recommendation line, formatted as the skill specifies.`;
@@ -153,7 +154,7 @@ Read plan.md — that's the plan to review. This is a standalone plan document,
 
 Proceed to Mode Selection. This is where the skill presents 4 mode options (SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION) to the user via AskUserQuestion. These options differ in kind (review posture), not in coverage.
 
-${captureInstruction(outFile)}
+${approachQuestionInstruction(outFile)}
 
 After writing the file, stop. Do not continue the review.`,
         workingDirectory: planDir,