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 zhuanggenhua/BoardGame --skill create-new-gamegit clone --depth 1 https://github.com/zhuanggenhua/BoardGameWrote 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/zhuanggenhua/boardgame/create-new-game)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/create-new-game"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/create-new-game/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/zhuanggenhua/boardgame/create-new-game"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/create-new-game.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 13 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 102 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 103 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00042 | $0.02897 |
| Opus 5 | $0.00021 | $0.01448 |
| Sonnet 5 | $0.00008 | $0.00579 |
| Haiku 4.5 | $0.00004 | $0.00290 |
Grade A, and why
create-new-game 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 3d 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.
创建新游戏工作流
职责边界
本 skill 只承载新 gameId 从规则 / 素材 intake 到骨架、实现、UI、验证的阶段路由和完成门槛。具体模板、命令、文件结构和长门禁放在 references/；主入口不复制正文。
- AI 规范维护不由本 skill 承担；回
.spec/knowledge/README.md和spec-steward。 - 已有游戏新增派系 / 角色 / 可玩单元不走本 skill；回
.spec/skills/add-new-faction/SKILL.md或对应专项 workflow。 - 产品方案、proposal、tasks、spec delta 和具体游戏范围管理归
openspec/；本 skill 只负责 AI 执行流程。 - 数据录入、资源链、UI gate、审计、E2E、音频、关键图片、支撑能力均以对应 standards / skills 为主源。
必读路由
按当前阶段只读必要 reference：
| 场景 | 先读 |
|---|---|
| 流程边界、worktree、OpenSpec、百游戏模式 | references/workflow-boundaries.md |
| 来源裁定、素材 / 规则 intake、资源准入 | references/preflight-gates.md |
| 阶段 0 一票否决 | references/intake-redlines.md |
| 目录骨架、manifest、domain 文件布局 | references/game-skeleton.md、references/manifest-generation.md |
| 机制分解、数据结构、权限矩阵 | references/mechanics-data-design.md |
| Board/UI、设计稿、截图链 | references/ui-implementation-gates.md |
| 收尾、i18n、教程、音频、关键图片、debug | references/finalization-checklist.md |
| 架构审查、项目结构、截图链模板 | 对应 references/*template*.md、references/project-structure.md |
若 reference 与 .spec/knowledge/standards/ 或专项 skill 冲突，先执行主源，并回头修正过时 reference。
现场和范围
- 新游戏默认建议独立 worktree，但创建、切换或派生分支前必须得到用户当轮明确授权。
- 一旦选定执行现场，后续读写、验证、截图和 OpenSpec 更新都必须落在同一现场。
- 共享基线改动和单游戏实现分开收口；误落到主工作区的新游戏实现不得顺手并入主线。
- 未获授权创建 worktree 时，只做读取、规则 / 素材核对、计划和证据整理；实施确实依赖隔离现场时，说明后果和最小授权动作。
阶段门槛
S0 Intake
未闭合以下内容前，不得进入目录骨架、Board/UI、机制实现、E2E、截图或完成汇报：
- 规则源、对照源和用户指定真相源；
- 对象全集、规则对象 × 素材数量对账；
- 正式素材、候选素材、参考图和排除项职责；
- 基础规则语义覆盖矩阵；
- 图面字段、空间载体、setup、资源用途和运行时素材需求。
新游戏的第一优先级是数据录入：凡是已经读取过的图片、图集、截图或裁图，必须先回填数据录入规范要求的图片登记表，完成图面数据、对象 / 槽位、最终处置和处置依据；不得先判断“这张图有没有用”再决定是否登记。卡牌描述、i18n、运行时定义和机制实现只能消费锁定后的录入合同。
缺口只能写成 blocked / disputed / out-of-scope / approved-programmatic 等可追溯状态，不能用占位素材、CSS 图形、示意图或 E2E 绿灯顶替。
新游戏的正式 OpenSpec proposal 也必须建立在 S0 之上：proposal 不是 intake 的替代物，而是基于已录入事实做架构、数据模型、流程和任务拆分的规划产物。无需录完全部卡库，但至少要录入能跑通目标主流程的规则对象、卡牌/能力效果、状态变化、玩家决策和所需素材；另需主动查询尚未录入的派系/角色特色机制，凡可能改变共享引擎、对象模型或流程边界的机制都必须写入风险和设计依据。
S1 骨架与 Manifest
Open Design 设计稿和 UI-facing 模型批准前，S1 只允许建立非 UI 目录骨架、manifest、domain 草稿、规则文件和资源索引；不得创建正式 Board、运行时 HUD 或玩家交互。设计稿批准后，再按 references/game-skeleton.md 补齐 Board、thumbnail、tutorial、audio、critical image resolver 和基础测试。主 skill 不维护代码模板。
What ships with it
11 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.
- references/architecture-review-template.md 3.8 KB
- references/basic-flow-screenshot-template.md 2.6 KB
- references/finalization-checklist.md 4.5 KB
- references/game-skeleton.md 5.4 KB
- references/intake-redlines.md 18 KB
- references/manifest-generation.md 473 B
- references/mechanics-data-design.md 11 KB
- references/preflight-gates.md 10 KB
- references/project-structure.md 2.6 KB
- references/ui-implementation-gates.md 14 KB
- references/workflow-boundaries.md 15 KB
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.
- 3d ago Changed · +5 lines 2cccdc2b3379
- 11d ago First seen · 160 lines · 42 tokens per session scan A bc4cfb7ec044
create-new-game is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 2,897 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 2026-08-30.
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…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
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.