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 sumo1/AI-GAME-COOL --skill snake-adventuregit clone --depth 1 https://github.com/sumo1/AI-GAME-COOLWrote 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/sumo1/ai-game-cool/snake-adventure)<a href="https://agentmods.dev/skills/sumo1/ai-game-cool/snake-adventure"><img src="https://agentmods.dev/badge/skills/sumo1/ai-game-cool/snake-adventure/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/sumo1/ai-game-cool/snake-adventure"><img src="https://agentmods.dev/badge/skills/sumo1/ai-game-cool/snake-adventure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.01112 |
| Opus 5 | $0.00023 | $0.00556 |
| Sonnet 5 | $0.00009 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
snake-adventure 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 12d 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.
What it actually says
贪吃蛇
经典贪吃蛇:键盘控制方向,吃食物增长身体,撞墙或撞自身结束。本 SKILL 由任务 260521-playable-snake-evolution 蒸馏,每条规则都来自真实 LLM 生成偏差的修正。
何时使用
用户提到 贪吃蛇 / snake / 蛇 / 吃豆豆(带方向键控制) 等关键词。
生成步骤
- canvas 元素 400-600 px 见方,
<canvas id="game">用 id 便于测试钩子 - 键盘事件绑到 document,不要绑到 button / canvas(否则需要 focus 才能控制)
- 同时支持方向键 + WASD:
if (k === 'ArrowUp' || k === 'w' || k === 'W') ... - dir + nextDir 解耦 实现反向键防呆:keydown 写 nextDir,下次 tick 判定再赋给 dir
- setInterval 持续驱动 tick(180-300ms),不要"按键时才移动"
- 每 tick 清画布:
ctx.clearRect(0, 0, w, h)或填充背景色 - food 与蛇不重叠:
placeFood()用 while 循环检测snake.some(s=>s.x===fx&&s.y===fy),重叠则重新随机 - score 用专门 DOM 元素:
<span id="score">0</span>,每次吃食物scoreEl.textContent = score - 游戏结束态明确:撞墙/自撞触发
clearInterval(timer)+ 显示 overlay + 鼓励而非惩罚的文案 + 提供"再来一局"重启入口 - 初始状态必须是"准备开始"而非"游戏结束":页面加载后 overlay 文案应是"准备好了吗?/ 开始游戏",按钮文案应是"开始游戏"——绝对不能初始就显示"游戏结束 / 再来一局"(那让用户和测试都误以为已经死了)。只有真撞墙后才切换为结束态。
评估重点
- 键盘事件必须绑到 document(绑 button/canvas 会导致需要先 focus 才能控制)
- 反向键被防呆(蛇向右走时按左键不能瞬间反向 → 否则秒死)
- 蛇在 setInterval 里持续移动,不是只在 keydown 时移动
- canvas 每 tick 清画布,无拖影
- 食物不能生成在蛇身上
- 吃食物分数真的涨(DOM 同步更新)
- 游戏结束态可见(overlay / alert / 状态变化),不是无声死亡
- 失败文案鼓励("再来一次"、"差一点点"),不要"你输了"这种打击
- 整页布局必须能在视口内完整呈现(含 canvas + 分数 + 方向键 / 控制条),不出滚动条:固定像素 600×600 + 60px 方向键叠加常会超过移动端视口。具体技法(vh / vmin / aspect-ratio / flex 自适应)任选,关键是儿童 / iPad 触屏场景下方向键被裁掉就等于游戏不能玩。
常见问题
- 按键无响应 → 检查 keydown 是否绑到 document;如果绑到 button/canvas 需要先 click 才能控制
- 蛇不动 → 移动逻辑应在 setInterval 里持续 tick,不要只在 keydown 时移动
- 瞬间死亡 → 反向键应忽略:用 dir + nextDir 解耦,tick 时检查
nextDir.x !== -dir.x才赋值 - 吃了食物分数没涨 → score 变量更新后必须
document.getElementById('score').textContent = score - canvas 拖影 → 每个 tick 必须 clearRect 整个画布,或 fillRect 整背景
- 食物和蛇重叠 → placeFood 用 while 循环检测重叠 + 重新随机
- 撞墙后画面卡死 → gameOver 必须 clearInterval(timer) + 显示结束 overlay 而不是只 return
What ships with it
1 file 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.
- 12d ago First seen · 55 lines · 47 tokens per session scan A f82984b6f27e
snake-adventure is a skill published in the GitHub repository sumo1/AI-GAME-COOL (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,112 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.