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 zenstory-ai/novel-to-game --skill game-buildgit clone --depth 1 https://github.com/zenstory-ai/novel-to-gameWrote 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/zenstory-ai/novel-to-game/game-build)<a href="https://agentmods.dev/skills/zenstory-ai/novel-to-game/game-build"><img src="https://agentmods.dev/badge/skills/zenstory-ai/novel-to-game/game-build/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/zenstory-ai/novel-to-game/game-build"><img src="https://agentmods.dev/badge/skills/zenstory-ai/novel-to-game/game-build.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 | $0.00151 | $0.01262 |
| Opus 5 | $0.00076 | $0.00631 |
| Sonnet 5 | $0.00030 | $0.00252 |
| Haiku 4.5 | $0.00015 | $0.00126 |
Grade A, and why
game-build 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- game-build — 100% identical, 21 lines differ
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
游戏构建执行
保护已批准的体验边界；正式生产时再保护已批准的美术边界。驱动实现模型完成真实可玩的候选，不在 构建阶段重新做概念、关卡或美术方向。
读取 build-brief-contract.md。白盒阶段必须已有 GAME_DESIGN.md；
完整候选还必须已有 ART_DIRECTION.md。缺产品决定时回对应 owner，不在 BUILD_BRIEF 就地发明。
产物语言由 PRODUCT_BRIEF.md 锁定；未锁定时跟随对话语言，不默认产出中文。
目标与自由
按 PRODUCT_BRIEF 锁定的平台、生产引擎、目标运行时、显示/输入、范围、分级和联网边界交付。
目标工具链不可用时不得自动改做网页；只有 brief 已批准替代运行时才可使用，并分开记录
targetRuntime、testedRuntime 与未覆盖项。
正式生产继承 ART_DIRECTION.md 的可观察视觉约束与批准目标图，在实际运行中验证焦点资产。
BUILD_BRIEF 只压缩产品边界、必须保真的体验事实、运行方式与完成证据，实现细节交给实现模型。
先声明 buildStage: whitebox|production 与 buildPath: template|custom。已有交互语法只有在能保留原作
独有动作、代价和世界回应时才采用；实时手感、空间、视线、物理或模板覆盖不了的核心动词走 custom。
白盒也必须选择能验证最大风险的形态，不能把所有项目降成文游。
当前会话能编码时直接实现；外部模型不可用时只交付构建说明，不声称游戏已生成。不要发送与原型 无关的完整受版权保护原文。
按能力读取可选合同
- 已选择 Blender 制作或修改可编辑三维资产时，读取 blender-asset-workflow.md； 不因项目是 3D 就默认采用 Blender 或安装 MCP。
- 采用生成式自由输入、知识权限、事件回放、存档迁移或
signature_command时，读取 playable-model-contract.md 的相关部分；普通游戏不另建一套平行状态模型。 - 语音策略不是
none时读取 tts-production-contract.md。TTS 优先构建期生成成本地资产；运行时远程合成须在 brief 批准，密钥只留受信服务端。 - 实际采用动态媒体时读取 generative-media-pipeline.md。已有批准 参考图时以图约束；工具与模型按当前环境选择，不写成跨项目默认。
共同构建循环
- 先实现一个最小但完整的核心循环：启动、真实输入、状态变化、结果和重开。范围不足时修范围， 不先堆审计材料。
- 实现 GAME_DESIGN 的状态、动作与结果；使用生成模型时，模型只解释输入和结果，规则器拥有提交权。
存在
signature_command时再执行可选合同的专属边界。 - 保留能复现问题的初态与输入路径，涉及随机性时固定 seed；修订后重放失败路径与相邻反例。
- 回写实际工具链、install/build/start 命令和版本；未知值写
NOT_AVAILABLE: 原因，不猜。
whitebox 到此按 build-brief-contract「完成证据」运行最窄检查并交回 design owner；设计修订后
重放受影响路径，直到最大风险已被实际暴露或当前方向被否决。
production 继续：
- 提供一条权威验证命令和最小可观察状态，使
game-qa能一次走完clean start → 核心动作 → 设计结果 → restart。 - 运行最窄的开发检查与启动 smoke，修复构建失败、阻断日志、资源失败和崩溃；替代运行时未覆盖的 目标平台输入、性能、打包或设备项写入 limitation。
- 达到 brief 的
targetFinish；更高完成度只处理已批准的焦点资产和招牌时刻，不制造与可玩闭环 无关的发布审计。 - 交给
game-qa；允许诊断、修复和复跑，最终事实必须来自修订后同一次完整验证，不能拼接旧 PASS。
What ships with it
6 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.
- 4d ago Changed · +1 lines 858623b8f652
- 7d ago Changed · -17 lines 09d235ef85d5
- 12d ago First seen · 85 lines · 151 tokens per session scan A 4aaf579704e8
game-build is a skill published in the GitHub repository zenstory-ai/novel-to-game (775 stars, last pushed today), licensed MIT. It adds 151 tokens to every session and 1,262 once invoked, about $0.0008 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
reversi-master
One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code (Moonshot) ,Qwen Code,Aider,OpenCode,MiMo Code (Xiaomi),ZCode (Z.AI),OpenClaw,Pi,OpenScience,Vibe-Trading,Claude Desktop (3P profile),ChatGPT desktop,OpenCode Desktop.
design-system
Guided, section-by-section GDD authoring for a single game system. Gathers context from existing docs, walks through each required section collaboratively, cross-references dependencies, and writes incrementally to file.
prototype
Concept prototype — validate the core idea is worth designing before writing GDDs. Run right after /brainstorm and /setup-engine. Routes to HTML, Engine, or Paper path based on game type. Produces a throwaway build and a PROCEED/PIVOT/KILL verdict.
setup-engine
Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
architecture-review
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL…