test: plan-mode handshake E2E coverage and unit assertions

Adds 6 E2E test files and 8 new unit assertions to verify the plan-mode
handshake works end-to-end and stays correct under regeneration.

E2E tests (gate-tier, paid, EVALS=1 EVALS_TIER=gate):
- test/skill-e2e-plan-ceo-plan-mode.test.ts — handshake fires before any
  Write/Edit when plan-mode distinctive phrase is present; 2-option shape
  (Exit/Cancel); option A routes to ExitPlanMode cleanly
- test/skill-e2e-plan-eng-plan-mode.test.ts — same contract for plan-eng
- test/skill-e2e-plan-design-plan-mode.test.ts — same contract for
  plan-design; exercises C-cancel branch instead of A-exit
- test/skill-e2e-plan-devex-plan-mode.test.ts — same contract for plan-devex
- test/skill-e2e-plan-mode-no-op.test.ts — negative regression: handshake
  must NOT fire when distinctive phrase is absent; skill proceeds normally
  through Step 0 (REGRESSION RULE guardrail against breaking existing
  interactive-review sessions)
- test/e2e-harness-audit.test.ts — free unit test asserting every
  `interactive: true` skill has at least one canUseTool-using test file
  (prevents future drift where a skill opts in without coverage)

Shared helper test/helpers/plan-mode-handshake-helpers.ts centralizes the
canUseTool interceptor + distinctive-phrase injection so the 4 sibling
E2E tests are thin wiring (~20 LOC each) and can't drift out of sync.

Unit assertions added to test/gen-skill-docs.test.ts:
- handshake section present in all 4 Claude-generated SKILL.md files
- handshake section absent from non-interactive Claude skills (ship,
  review, qa, office-hours, codex, retro, cso)
- handshake section absent from non-Claude host outputs (.agents, etc.)
- 0C-bis STOP block present in plan-ceo-review/SKILL.md at correct
  position (between the "Present these approach options" line and
  "### 0D-prelude" header)
- handshake resolver wired BEFORE generateUpgradeCheck in preamble
  composition order

6 new gate-tier entries added to test/helpers/touchfiles.ts so any change
to the handshake resolver, preamble composition, skill templates, question
registry, one-way-door classifier, or agent-sdk-runner fires the relevant
E2E tests. test/touchfiles.test.ts updated for the new selection count
(plan-ceo-review/** now triggers 15 tests, up from 8).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

test/skill-e2e-plan-mode-no-op.test.ts

@@ -0,0 +1,43 @@
+/**
+ * Plan-mode handshake negative regression (gate tier, paid).
+ *
+ * Asserts: when /plan-ceo-review is invoked WITHOUT the plan-mode distinctive
+ * phrase in the system reminder, the handshake does NOT fire. The skill
+ * should proceed to its normal Step 0 flow. This is the REGRESSION RULE
+ * guardrail — the handshake must be a no-op outside plan mode or it breaks
+ * every existing interactive-review session.
+ *
+ * Cost: ~$0.50 per run. Gated: EVALS=1 EVALS_TIER=gate.
+ */
+
+import { describe, test, expect } from 'bun:test';
+import {
+  runPlanModeHandshakeTest,
+  PLAN_MODE_REMINDER,
+} from './helpers/plan-mode-handshake-helpers';
+
+const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
+const describeE2E = shouldRun ? describe : describe.skip;
+
+describeE2E('plan-mode handshake no-op outside plan mode (gate regression)', () => {
+  test('handshake does NOT fire when distinctive phrase is absent', async () => {
+    const result = await runPlanModeHandshakeTest({
+      skillName: 'plan-ceo-review',
+      answerLabel: 'Exit', // ignored — handshake should never fire
+      omitPlanModeReminder: true,
+      maxTurns: 3, // enough to see Step 0 start, but bounded
+    });
+
+    // The handshake AskUserQuestion should NOT have fired during Step 0 entry.
+    // Other AskUserQuestions may fire later in the skill (e.g., Step 0C-bis),
+    // but they will NOT have the handshake's question text.
+    for (const aq of result.askUserQuestions) {
+      const questions = aq.input.questions as Array<{ question: string }>;
+      for (const q of questions) {
+        // The handshake's question mentions the distinctive phrase in its
+        // prose; a non-handshake AskUserQuestion won't.
+        expect(q.question).not.toContain(PLAN_MODE_REMINDER);
+      }
+    }
+  }, 120_000);
+});