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 instructions/g0v/moedict.tw/agents-mdgit clone --depth 1 https://github.com/g0v/moedict.twWrote 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/instructions/g0v/moedict.tw/agents-md)<a href="https://agentmods.dev/instructions/g0v/moedict.tw/agents-md"><img src="https://agentmods.dev/badge/instructions/g0v/moedict.tw/agents-md.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 | $0.19363 | $0.19363 |
| Opus 5 | $0.09681 | $0.09681 |
| Sonnet 5 | $0.03873 | $0.03873 |
| Haiku 4.5 | $0.01936 | $0.01936 |
Grade A, and why
moedict.tw AGENTS.md 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 — 735 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — cf-moedict-webkit-neo（moedict.tw）
萌典（moedict）字典查詢網站的現行主站程式碼：React + TypeScript + Vite 前端、 Cloudflare Workers 後端、R2 儲存。本檔是給 AI agent 與新進開發者的工作手冊—— 內容以「未來 session 直接可用」為準，改動架構時請同步更新。
專案定位（多個 surface，別搞混）
| Surface | 是什麼 | 原始碼 |
|---|---|---|
| www.moedict.tw | 現行主站：本 repo 的 Worker cf-moedict-webkit-neo + R2 |
本 repo |
| www.moedict.org | 凍結的舊版靜態前端（GitHub Pages），只收安全性修正 | ~/w/moedict-webkit（gh-pages） |
| 行動 App | Capacitor 離線版，資料由本 repo data/dictionary 供給 |
~/w/moedict-app |
- 裸網域
moedict.tw會 301 到www.moedict.tw——線上驗證一律打www。 - 舊版
~/w/moedict-webkit的view.ls是 UI 行為的 ground truth： 移植或修 UI 迴歸時先讀它，不要憑猜測（例：h1.title內的 DOM 順序）。
語言代碼（四本字典）
| 代碼 | 字典 | Hash 前綴 | 路由 | pack 目錄 |
|---|---|---|---|---|
a |
華語（國語辭典） | # |
/ |
pack/ |
t |
臺灣台語（閩南語） | #' |
/' |
ptck/ |
h |
臺灣客語 | #: |
/: |
phck/ |
c |
兩岸詞典 | #~ |
/~ |
pcck/ |
（舊版 CLAUDE.md 此表有誤，以上為正確對應。）
技術棧與目錄結構
- 前端：React 19、TypeScript、Vite+（Vite 8）、react-router-dom v7
- 後端：Cloudflare Workers（
worker/index.ts，經@cloudflare/vite-plugin建置） - 儲存：R2（
FONTS/ASSETS/DICTIONARY三個 binding） - 工具鏈：Vite+ 統一 dev/build/test/lint/format/runtime/package-manager 入口；
vite.config.ts同時持有 Vite、Vitest projects、Oxlint 與 Oxfmt 設定。 - 套件管理：Vite+ 管理的 Bun（
vp install、vp run <script>；lockfile 是bun.lock）。
src/
pages/ # DictionaryPage（核心詞條頁）、Dictionary-a/c/h/t、ListView、
# RadicalView、RadicalDetailView、StarredPage、About、Privacy
components/ # Layout、navbar、searchbox、sidebar、StrokeAnimation、
# CharacterImageView、AssetLoader、InlineStyles、user-pref
api/ # Worker 端 API handler（handleDictionaryAPI、handleLookupAPI、
# handleListAPI、cache.ts 快取政策）
oembed/ # /embed/<詞> 卡片 + /api/oembed
ssr/ # head.ts（伺服端 <head> 注入）
hooks/ utils/ # decorateRuby、pinyin 轉換、dictionary-route 等
worker/
index.ts # Worker 入口 + dispatch() 路由表
data/
dictionary/ # 字典資料（真實來源，上傳至 R2；見「字典資料格式」）
assets/ # 舊版前端資產（styles.css、字型、JS；上傳至 R2）
scripts/ # build-search-index、build-pinyin-lookup、merge-coverage 等
commands/ # upload_dictionary.sh、upload_assets.sh、fetch-moe-stroke.mjs、sync-moe-stroke-corpus.mjs
tests/ # unit / integration / e2e 三層
memory/MEMORY.md # 跨 session 的架構筆記（與本檔互補）
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 First seen · 735 lines · 19,363 tokens per session scan A 83644943d914
moedict.tw AGENTS.md is an instructions file published in the GitHub repository g0v/moedict.tw (11 stars, last pushed 11d ago), licensed CC0-1.0. It adds 19,363 tokens to every session, about $0.0968 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.