fix(web): address review-work findings (Category Routing, OG dims, e2e drift)

Three reviewer-flagged corrections, none with UX impact:

- Category Routing block on the landing page still showed pre-v4.0 model
  labels (`ultrabrain → GPT 5.4`, `deep → GPT 5.3 Codex`, `quick →
  Claude Haiku 4.5`) which contradicted the rest of the page after the
  model refresh. Pinned them to the actual primary chains
  (`ultrabrain → GPT 5.5 xHigh`, `deep → GPT 5.5 Medium`,
  `quick → GPT 5.4 Mini`). Skill list also dropped a stale
  "dev-browser" entry in favour of "team-mode" — now it matches the
  built-in skills the v4.0 release ships.
- OG/Twitter image metadata in app/layout.tsx claimed the hero was
  1536×1024 — actual file is 1024×683. Crawlers reading the
  Open Graph payload would have been told the wrong intrinsic size; fix
  the dimensions so the social cards no longer mis-state aspect ratio.
- e2e/example.spec.ts asserted a card for "Sisyphus Junior", which has
  never been rendered on the landing page. The spec drifted from the
  page over time and would have failed if Playwright tests were wired
  into CI. Pruned the list to the nine agents actually rendered.

web/e2e/example.spec.ts

@@ -26,7 +26,7 @@ test.describe("Landing Page", () => {
     await expect(installCommand).toBeVisible()
   })
 
-  test("renders all 10 agent cards", async ({ page }) => {
+  test("renders all rendered agent cards", async ({ page }) => {
     // given
     await page.goto("/")
 
@@ -41,7 +41,6 @@ test.describe("Landing Page", () => {
       "Metis",
       "Momus",
       "Atlas",
-      "Sisyphus Junior",
     ]
     for (const name of agentNames) {
       await expect(page.getByText(name, { exact: true }).first()).toBeVisible()