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 logic-puzzlegit 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/logic-puzzle)<a href="https://agentmods.dev/skills/sumo1/ai-game-cool/logic-puzzle"><img src="https://agentmods.dev/badge/skills/sumo1/ai-game-cool/logic-puzzle/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/logic-puzzle"><img src="https://agentmods.dev/badge/skills/sumo1/ai-game-cool/logic-puzzle.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 | $0.00043 | $0.00523 |
| Opus 5 | $0.00022 | $0.00262 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
logic-puzzle 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 9d 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
逻辑推理大师
逻辑推理游戏，包含数列规律、图形排序、条件推理等题型，适合 8-12 岁儿童。
何时使用
用户提到逻辑、推理、数列、规律、排序、思维训练、智力题等关键词时激活此 Skill。
生成步骤
- 确定题目类型比例（数列/图形排序/逻辑推理/数学应用题）
- 参考
assets/template.html的多题型切换和解析显示逻辑 - 根据用户需求调整：
- 难度级别（简单规律/多步推理/复杂条件判断）
- 数值范围和运算复杂度
- 是否显示解题思路和解析
- 计时挑战模式或自由练习模式
- 可加入提示系统（消耗分数获取提示）
- 调用 generateGame 生成完整 HTML
- 调用 evaluateGame 检查质量
评估重点
- 题目逻辑正确，答案无误
- 数列规律清晰可发现
- 逻辑推理题的条件完整无歧义
- 干扰选项合理（不能太明显也不能太刁钻）
- 解题解析清晰易懂
- 题目难度匹配 8-12 岁认知水平
- 计分和进度显示正确
- 游戏完成后有成绩评价和鼓励
常见问题
- 谜题无解或多解 → 在生成谜题后验证唯一解，使用回溯算法确认有且仅有一个正确答案
- 提示功能无效 → 检查提示逻辑是否正确排除已知信息，确保提示后缩小解空间
- 难度等级无区分 → 通过控制变量数量和约束条件数量来区分 easy/medium/hard
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.
- 9d ago First seen · 47 lines · 43 tokens per session scan A d80127cd3a95
logic-puzzle is a skill published in the GitHub repository sumo1/AI-GAME-COOL (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 523 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
gentleman-trainer
Vim Trainer RPG system patterns for Gentleman.Dots. Trigger: When editing files in installer/internal/tui/trainer/, adding exercises, modules, or game mechanics.
game-builder
Convert any topic into playable browser games. Types: trivia, matching, word puzzles, adventure games. Uses Phaser.js or Kaboom.js.
teach-me
Teach the user end-to-end browser game development over multiple sessions — design, engine, art, audio, juice, multiplayer, shipping — by building real games together. Use when the user wants to LEARN to make games themselves: 'teach me game development', 'I want to learn to make games', 'teach me Phaser', 'how do…
hr-game-development
Help HR and recruiting teams hire and assess game development candidates across engineering, design, and art disciplines. Use when asked to write a game developer job description, create a gameplay engineer interview, assess a game designers portfolio, build a game studio leveling framework, or similar…
tutorial-workflow
A workflow for designing, reviewing, and testing tutorials and new-player onboarding for a game. It checks whether the tutorial teaches the game’s goals, turns, and cause-and-effect actions rather than merely listing buttons or reading like a rulebook.
godot-genre-educational
Expert blueprint for educational games including gamification loops (learn/apply/feedback/adapt), progress tracking (student profiles, mastery %), adaptive difficulty (target 70% success rate), spaced repetition, curriculum trees (prerequisite system), and visual feedback (confetti, XP bars). Use for learning apps…