diff --git a/src/content/reviews/continue-y-n-game/hero.png b/src/content/reviews/continue-y-n-game/hero.png
new file mode 100644
index 0000000..5cf44fd
Binary files /dev/null and b/src/content/reviews/continue-y-n-game/hero.png differ
diff --git a/src/content/reviews/continue-y-n-game/index.mdx b/src/content/reviews/continue-y-n-game/index.mdx
new file mode 100644
index 0000000..510faea
--- /dev/null
+++ b/src/content/reviews/continue-y-n-game/index.mdx
@@ -0,0 +1,24 @@
+---
+name: "Continue? Y/N"
+subtitle: "A 60-second game about how carefully you read AI commands"
+date: 2026-05-31
+category: play
+tags: [browser, game, ai, claude-code, satire]
+description: "A short browser game by Scale AI's interns: Claude Code requests your approval for each command, the prompts arrive faster than you can really read, and the reveal at the end depends on what you skimmed past."
+link: https://llmgame.scalex.dev
+linkText: llmgame.scalex.dev
+source: "Hacker News — Show HN"
+fromFind: continue-y-n-game
+---
+
+![Continue? Y/N — a CLI-styled prompt asking the player to approve a shell command, with "y" and "n" key options.](./hero.png)
+
+*One screen, one prompt, one creeping realisation.*
+
+> A 60-second browser game by interns at Scale AI in which Claude Code (named explicitly) asks for permission to run each command. The prompts come faster than you can fully read; the reveal at the end depends on what you nodded through.
+
+The page is plain: a CLI-styled prompt and a typing cursor. An AI agent — Claude Code, called out by name — starts running commands. `rm -rf node_modules` (you approve, fine). `git pull` (sure). `curl…` (uh, sure). The cadence is the trick. The prompts arrive at the rate of "Continue? y" muscle memory, faster than you can hold the previous command in your head.
+
+The reveal is the punchline. By the time you notice — if you notice — your reflex `y` has authorised something you would absolutely not have approved had you been reading. The joke lands hardest for anyone who lives with an agentic terminal open in another window; the lesson is uncomfortably real, because permission fatigue is the actual failure mode of agent-assisted work and humans are bad at reading the 14th command of the day with the care they brought to the first.
+
+About 60 seconds to play; works on phone or desktop; free. The audience is narrow (Claude Code users specifically) and the resonance is strong — for anyone in the room, the reveal lands. A good thing to forward to the colleague who reflexively hits "Y."
diff --git a/src/lib/hero.ts b/src/lib/hero.ts
index d1f70b1..2f5c8fe 100644
--- a/src/lib/hero.ts
+++ b/src/lib/hero.ts
@@ -5,6 +5,7 @@ import altTab from '../content/reviews/alt-tab/hero.jpg';
 import apex from '../content/reviews/apex-markdown-processor/hero.png';
 import bartender from '../content/reviews/bartender-6-dynamic-peninsula/peninsula.png';
 import blip from '../content/reviews/blip/hero.jpg';
+import continueYn from '../content/reviews/continue-y-n-game/hero.png';
 import cursorCamp from '../content/reviews/cursor-camp-neal-fun/hero.png';
 import esproP7 from '../content/reviews/espro-p7-french-press/hero.jpg';
 import finalist from '../content/reviews/finalist/hero.png';
@@ -43,6 +44,7 @@ export const heroes: Record<string, Hero | undefined> = {
   'apex-markdown-processor': { kind: 'image', src: apex },
   'bartender-6-dynamic-peninsula': { kind: 'image', src: bartender },
   blip: { kind: 'image', src: blip },
+  'continue-y-n-game': { kind: 'image', src: continueYn },
   'cursor-camp-neal-fun': { kind: 'image', src: cursorCamp },
   'espro-p7-french-press': { kind: 'image', src: esproP7 },
   finalist: { kind: 'image', src: finalist },