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 agentmods add skills/tiankonglan/tomewiki/docsnpx skills add tiankonglan/TomeWiki --skill docsgit clone --depth 1 https://github.com/tiankonglan/TomeWikiWrote 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/tiankonglan/tomewiki/docs)<a href="https://agentmods.dev/skills/tiankonglan/tomewiki/docs"><img src="https://agentmods.dev/badge/skills/tiankonglan/tomewiki/docs.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01473 |
| Opus 5 | $0.00000 | $0.00737 |
| Sonnet 5 | $0.00000 | $0.00295 |
| Haiku 4.5 | $0.00000 | $0.00147 |
Grade A, and why
docs 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skill：第一轮建站
本文给人看：克隆模板之后，怎样用自带 skill 把「Example Game」换成自己的站。
给 Agent 执行的步骤在：
.claude/skills/tomtwiki-quick-start/SKILL.md（Claude Code）.cursor/skills/tomtwiki-quick-start/SKILL.md（Cursor）.agents/skills/tomtwiki-quick-start/SKILL.md（Codex）
三份随仓库走，不用再装 marketplace skill。手工改配置见 QUICKSTART.md。
它做什么
第一轮只做站身份，不做内容生产：
| 会改 | 不会改 |
|---|---|
| 站名、域名、游戏名、免责声明 | 路由、组件、src/app/** |
| 首页文案（积木结构不变） | 登录、数据库、支付 |
| SEO title / description / keywords | content/guides/、content/entities/ 里的种子正文 |
| 主题预置 + 品牌色 | 分类文件夹 slug |
| logo / favicon / OG 图 | 编造 Steam ID、官宣口吻 |
跑完你得到的是「看起来像这个游戏的空壳」，攻略和资料库还要自己填。
环境
- Node.js 24、pnpm 10.34.5（与 CI 一致）
- Cursor、Claude Code 或 Codex 打开的是克隆后的仓库根目录（能看见
.claude/skills//.agents/skills/）
git clone https://github.com/tiankonglan/tomtwiki.git my-game-wiki
cd my-game-wiki
pnpm install
怎么唤起
在对话里用自然语言即可。skill 的 description 里带了「建站 / 快速接入 / 改成自己的站 / Example Game」，Agent 应能自己选中。
没被选中时：
- Cursor：
/或@技能列表里找tomtwiki-quick-start - Claude Code：
/tomtwiki-quick-start - Codex：
$tomtwiki-quick-start
提示词模板
最少只要游戏名和域名：
把这个模板改成《Hades II》的非官方攻略站。
域名 hades2.wiki。
信息越全，第一轮越少 TODO:：
把这个模板改成《Hades II》的非官方粉丝攻略站。
- 域名：hades2.wiki
- 简称：Hades 2
- 一句话：构筑、Boss 机制、热更新对照表
- 品牌色：#C45C26
- 主题：tactical
- 当前版本：1.0
- 状态：Early Access（可留空）
- Steam App ID：1145350（没有就不要编）
- 发行商：Supergiant Games（免责声明用）
- 不要加登录或数据库
主题只能是：tactical（默认）/ pixel / neon / aurora / sakura。含义见 THEMES.md。
你需要准备什么
| 字段 | 必须？ | 说明 |
|---|---|---|
| 游戏全名 | 是 | |
| 域名 | 是 | 只写 hostname，不要 https:// |
| 简称、tagline、版本 | 否 | 有默认 |
| 品牌色、主题 | 否 | 未给则按品类猜，可事后改 |
| Steam ID | 否 | 禁止猜测 |
| logo / 方形 emblem | 否 | 没有则跑仓库自带 scripts/gen-brand-assets.mjs |
| Key art、实机截图、预告片 URL | 否 | Key art 用 cover-split，干净实机截图用 gameplay-panel，预告片用 video-center |
| 分析 ID | 否 | 没给就留空 |
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.
- 5d ago First seen · 124 lines · 0 tokens per session scan A 14ffa1e2f20b
docs is a skill published in the GitHub repository tiankonglan/TomeWiki (6 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,473 tokens. 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
merge-seed
Merge upstream React Starter Kit updates (the seed remote) into main, preserving this project's identity, scope, and behavior. Use when asked to sync, pull, or merge the seed / starter kit / upstream template.
wot-ui-unocss-preset-guide
指导安装、配置并使用 @wot-ui/unocss-preset。Invoke when 用户询问该预设的接入、配置、使用示例或常见问题排查。.
starter-cleaner
将 wot-starter v2 模板精简为最小可开发状态，移除文档、演示分包、生成文件和 monorepo 配置，并同步清理相关 Vite 与 package.json 配置。用户要求“清理模板”“移除示例”“生成最小模板”“精简 wot-starter v2”时使用。.
anvil-new-article
从用户提供的素材(口述要点/YouTube 视频/别的攻略/原始数据)直接生成一篇符合 AnvilWiki schema 的 MDX 文章页,自动填 frontmatter(title/description/category/tags/summary/boss 等),写完后自动跑校验。视频素材走 Step 0 抓字幕再成文。触发词:写文章 / 生成攻略页 / 视频转攻略 / new article / 帮我把这些内容做成页面。.
anvil-refresh
内容新鲜度巡检——扫描全站 lastModified 超 90 天的时效性文章(bosses/tier-list)、codes 页日期、sitemap 覆盖缺口,输出一份"该更新什么"的优先级清单。触发词:内容巡检 / 哪些文章过期了 / freshness check / 该更新什么。.
wot-ui-cli
回答、使用、调试 @wot-ui/cli 时使用。关键词：wot、@wot-ui/cli、CLI、MCP、doctor、usage、lint、list、info、doc、demo、token、changelog、extract、wot mcp。适用于命令查询、参数说明、MCP 接入、本地调试、数据提取与 open-wot 仓库维护。.