test: clean up the paid eval lane (B1-B4, B6, B7)

- B1: delete paid files that assert nothing or cannot pass meaningfully:
  skill-llm-eval-spec and skill-e2e-spec-execute (test.todo), gemini-e2e
  (+ gemini-session-runner; no gemini CLI in CI), ship-idempotency (red
  since v1.63), the two opus-4-7 *-sonnet overlay wrappers, conductor-prose
  (+ its source-evaluation replay), codex-e2e-plan-format; drop their keys,
  scripts and census rows.
- B2: skill-llm-eval grades browse/sections/command-list.md with one union
  judge that also carries the baseline score pin; regression-vs-baseline
  deleted (paid run: pass, c4/c4/a4).
- B3: memory-pipeline, ios-qa, ios-qa-swift-build and plan-tune-cathedral
  make no model calls; renamed out of the paid glob so they run on every
  PR. Swift builds need GSTACK_TEST_SWIFT=1; device stub deleted.
- B4: codex-e2e*, outside-voice, aside and ios-device cannot run in the CI
  image; excluded from the weekly lane with a tracked re-entry condition.
- B6: fold opus-47's negative routing controls into skill-routing-e2e
  journey-negatives (paid run: 3/3 unrouted) and delete the file.
- B7: delete the never-green brain-privacy-gate eval; a free
  gstack-skill-start test now proves consent precedes artifacts egress.

test/plan-review-calibration.test.ts

@@ -26,12 +26,11 @@ test('semantic helper changes also select the separate DX analysis calibration',
     // Its direct behavioral consumers extend the unchanged helper-only set.
     if (file === 'test/plan-review-cases.test.ts') expected.push(
       'plan-eng-review', 'plan-eng-review-artifact', 'plan-review-report',
-      'plan-eng-review-plan-mode', 'plan-mode-no-op', 'conductor-prose',
+      'plan-eng-review-plan-mode', 'plan-mode-no-op',
       'carve-section-loading', 'autoplan-chain-pty', 'plan-eng-finding-floor',
       'plan-eng-review-format-coverage', 'plan-eng-review-format-kind',
       'plan-ceo-review-prosons-cadence', 'plan-review-prosons-format',
-      'codex-offered-eng-review', 'codex-plan-eng-format-coverage',
-      'codex-plan-eng-format-kind', 'plan-eng-coverage-audit', 'autoplan-dual-voice',
+      'codex-offered-eng-review', 'plan-eng-coverage-audit', 'autoplan-dual-voice',
     );
     expect(selectTests([file], E2E_TOUCHFILES, []).selected.sort()).toEqual(
       expected.sort());