Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kyh/vibedgames --skill game-playbookgit clone --depth 1 https://github.com/kyh/vibedgamesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kyh/vibedgames/game-playbook)<a href="https://agentmods.dev/skills/kyh/vibedgames/game-playbook"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/game-playbook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kyh/vibedgames/game-playbook"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/game-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.02282 |
| Opus 5.5 | $0.00012 | $0.00913 |
| Sonnet 5.5 | $0.00006 | $0.00456 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
game-playbook scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crafting a great game
The platform promise is "studio-grade games from a prompt." The gap between a tech demo and that is two things: the right build order and craft. This skill is the playbook. The engine/asset/deploy skills own the pieces; this owns how they fit together and how to make the result fun.
The recipe (a complete game from "make a game")
Do these in order — don't write the game loop before you have art, and don't ship before the craft pass.
-
Scaffold.
vg new <slug> --engine phaserfor 2D,--engine threejsfor 3D. (See thephaser/threejsskills.) The template is a skeleton, not a game — you will replace its placeholder scene and logo. Looks matter? (user names a game it should look like, or wants a polished/studio pass) — lock 4–8 real reference screenshots and a per-game visual bar before any art:references/visual-bar.md. A locked bar replaces step 2's order with that file's light-first order (light and grade over placeholders → surfaces → density → HUD → motion). -
Generate the art FIRST. The route depends on the engine you scaffolded:
2D (
--engine phaser) — seepixel-art. Order matters:- hero character → directional walk sheets (
walk-down/up/side, left = mirror) → background-remove (Bria) → normalize to exact power-of-two frames. - enemies / pickups / projectiles.
- impact + ability VFX on PURE BLACK (slash arcs, explosions, muzzle
flashes) — render them with
BlendModes.ADDso black is free transparency, no alpha pass needed. A generated video, sliced into a frame strip, makes great fire/explosion (seepixel-artRecipe 5). - ground/tiles or a parallax/arena backdrop. Replace the template's logo/bg — never ship placeholder art.
3D (
--engine threejs) — meshes and props, not sprite sheets:- hero characters and organic shapes → Meshy via
model-catalog(text-to-3d / image-to-3d); rigged animated characters →regenerate-3d. - hero props that must hinge, open, detach, or break (chests, doors,
levers) →
image-to-threejs: a procedural factory with a pivot/socket rig, built from one generated reference image. - loading, normalizing, and placing any of it → the
threejsskill'sreferences/generated-assets.md. - repeated set dressing → primitives/instances or a kit GLB, never a fresh generation per copy.
- hero character → directional walk sheets (
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 25d ago Changed 129079e01f30
- 1mo ago Changed · +21 lines e79a1f579cb3
- 1mo ago Changed · -93 tokens per session b7c6d8caea42
- 2mo ago First seen · 144 lines · 123 tokens per session scan A 8445f6ec9a54
game-playbook is a skill published in the GitHub repository kyh/vibedgames (61 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,282 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
game-playbook compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| game-playbookkyh/vibedgames | Skill | 61 | 2d ago | MIT | A | 30 | Claude Code |
| verifymeursyphus/ssgoi | Skill | 1.0k | 3d ago | MIT | A | 26 | Claude Code |
| quality-engineering-playwright-cliHoangNguyen0403/agent-skills-standard | Skill | 583 | yesterday | MIT | A | 62 | Claude Code, Codex |
| quality-engineering-playwright-pom-generationHoangNguyen0403/agent-skills-standard | Skill | 583 | yesterday | MIT | A | 69 | Claude Code, Codex |
| supabasemartineserios/thebrana | Skill | 3 | today | MIT | A | 58 | Claude Code |
| playwright-e2elroy-stack/ai-pod-store | Skill | 1 | 11d ago | none | A | 86 | Claude Code |
| next-cache-components-optimizervercel/next.js | Skill | 143k | yesterday | MIT | A | 123 | Claude Code |