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 QiHuang02/world-book-mcp --skill world-book-mcp-skillgit clone --depth 1 https://github.com/QiHuang02/world-book-mcpWrote 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/qihuang02/world-book-mcp/world-book-mcp-skill)<a href="https://agentmods.dev/skills/qihuang02/world-book-mcp/world-book-mcp-skill"><img src="https://agentmods.dev/badge/skills/qihuang02/world-book-mcp/world-book-mcp-skill/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/qihuang02/world-book-mcp/world-book-mcp-skill"><img src="https://agentmods.dev/badge/skills/qihuang02/world-book-mcp/world-book-mcp-skill.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 | $0.00112 | $0.02433 |
| Opus 5 | $0.00056 | $0.01216 |
| Sonnet 5 | $0.00022 | $0.00487 |
| Haiku 4.5 | $0.00011 | $0.00243 |
Grade A, and why
world-book-mcp-skill 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
world-book-mcp v5
以 world-book-mcp 工具输出为唯一事实源。不要手写最终 .card.json 或 .worldbook.json;最终 JSON 必须从项目 plan.md、draft YAML 和 source/ 文件生成。
必须流程
- 判定请求类型:新建原创/二创、导入/修复已有 JSON、断点续写、校验交付,或局部修改。
- 只读取本次任务需要的
references/文件。 - 创建或定位项目:
- 新项目:在知道最小项目名和输出目标后尽早调用
init_project,先创建可写入的plan.md。 - 已有 JSON:调用
import_existing_json,再用query_project检查导入结果。 - 续写/修改:调用
resume_project或query_project。
- 新项目:在知道最小项目名和输出目标后尽早调用
- 定稿设计或写长内容前执行 grill-me 询问。每轮只问一个关键问题,给出推荐答案,用户回答后立即用
update_plan记录。 - 长内容只能通过
write_source_file写入;生成配置通过write_draft或configure_draft写入draft/card.yaml、draft/worldbook.yaml、draft/assets.yaml。 - 交付前校验:
- 始终运行
validate_project。 - 启用或修改 MVU 时运行
validate_mvu。 - 仅在导入/旧项目存在可修复问题时使用
repair_project。
- 始终运行
- 用
generate_json生成最终 Tavern JSON。 - 完整交付前运行
check_delivery,再返回 exports 路径和校验/构建摘要。
明月秋青风格适配原则
本 skill 可吸收“明月秋青写卡预设”的创作方法论,但不能原样搬运其越权、破限、强制思维链、伪人格绑定或未审计外链脚本。
可吸收:
- 世界观 A/B/C 判定、最小设定集、概念锚点。
- 角色基础、性格调色盘、三面性、二次解释、衣柜、NPC、角色速览、开场白大纲。
- 中文 YAML 结构、XML-wrapped YAML、白描、绝对零度、反八股。
- MVU 五件套、状态栏、EJS 多阶段人设、前端美化、regex 清理与美化的工程化模板。
必须过滤:
- 不要求或输出真实思维链;regex 只能清理/美化旧卡中的辅助块。
- 不复制破限、越权、安全规避、现实危害或未成年人性内容指令。
- 不默认加载第三方 Tavern Helper 外链;脚本必须显式写入
source/tavern-helper/并通过 assets 声明与校验。 - 不把“AI/模型/提示词/世界书/角色卡”写入成品叙事内容。
硬性规则
- 所有需求、决策、风险、验收标准和验证记录都写进
plan.md。 - 每轮 grill-me 回答必须立即
update_plan,不得攒多轮后批量记录。 - 角色卡
description必须严格等于"";人设、背景、关系和世界事实写进世界书条目。 - 长文本、MVU、HTML、regex、EJS、Tavern Helper 正文放入
source/,不要内联进 draft YAML。 - 每个世界书条目都必须开启
preventRecursion: true和excludeRecursion: true。 constant: false的绿灯条目必须至少有一个 key。- 不主动添加 MVU、HTML 状态栏、regex、EJS 或 Tavern Helper;只有用户明确要求或需求明显需要时才启用。EJS 依赖 MVU。
- 开场白和世界内容不得预设
{{user}}的性别、外貌、行动、心理或无法确认的身份。 - 启用 HTML 状态栏或 MVU 时,开场白必须保留
<StatusPlaceHolderImpl/>。 - 校验没有 blocking error 且 exports 已生成前,不得宣称完整交付。
创作输出风格
- 创作内容优先用中文 YAML 结构,2 空格缩进,中文键名,必要时使用 XML 标签包裹。
- 角色条目写行为、关系、边界和冲突;少写抽象评价。
- 世界观条目写会影响行动和剧情的事实,不写百科堆料。
- 开场白先大纲锚定,再写正文;以可互动场景收尾。
- 按
references/rules.md检查禁词、白描、具体性、语料纯净度、第四面墙和{{user}}边界。
What ships with it
19 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.
- agents/openai.yaml 262 B
- references/character.md 23 KB
- references/composition.md 3.0 KB
- references/draft-yaml.md 4.4 KB
- references/ejs.md 4.3 KB
- references/entries.md 2.2 KB
- references/first-message.md 2.7 KB
- references/frontend-beautify.md 3.4 KB
- references/html-statusbar.md 4.0 KB
- references/import-repair.md 2.6 KB
- references/mvu.md 6.5 KB
- references/plan-md.md 1.7 KB
- references/regex.md 4.1 KB
- references/requirements.md 1.2 KB
- references/resume.md 764 B
- references/rules.md 4.0 KB
- references/validation.md 3.2 KB
- references/workflow.md 1.4 KB
- references/worldbuilding.md 8.7 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.
- 12d ago First seen · 133 lines · 112 tokens per session scan A 1db40c6d0cc1
world-book-mcp-skill is a skill published in the GitHub repository QiHuang02/world-book-mcp (21 stars, last pushed 3mo ago), licensed MIT. It adds 112 tokens to every session and 2,433 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…