Borrowing it
Nothing to install: this file belongs to yazelin/ipas-ai-quiz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yazelin/ipas-ai-quiz/master/AGENTS.mdgit clone --depth 1 https://github.com/yazelin/ipas-ai-quizWrote 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/yazelin/ipas-ai-quiz/agents-md)<a href="https://agentmods.dev/instructions/yazelin/ipas-ai-quiz/agents-md"><img src="https://agentmods.dev/badge/instructions/yazelin/ipas-ai-quiz/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 5.1 | $0.02897 | $0.02897 |
| Opus 5 | $0.01448 | $0.01448 |
| Sonnet 5 | $0.00579 | $0.00579 |
| Haiku 4.5 | $0.00290 | $0.00290 |
Grade A, and why
ipas-ai-quiz 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 8d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — 給 AI 代理 / 貢獻者的修改指南
這份是讓「你(或你的 AI agent)clone 本 repo 後,能安全地擴充、改題、改功能」的說明。 本站是純靜態前端(無框架、無 build),題庫是 JSON,後端只有一個選用的 Cloudflare Worker。
檔案地圖
| 檔案 | 作用 | 改它要注意 |
|---|---|---|
index.html |
版面 + 全部 CSS(inline <style>)+ PWA head |
改到快取檔請 bump sw.js 版號 |
app.js |
全部前端邏輯(ES module,vanilla JS) | DOM 操作集中在這 |
core.js |
純邏輯(Leitner、計分、統計、出題優先序),有單元測試 | 改完跑 node core.test.mjs |
core.test.mjs |
core.js 的測試 |
改邏輯要同步更新斷言 |
questions.json |
題庫(主要要改的就是這個) | 見下方 schema |
concepts.json |
每日 AI 觀念卡池 | { "cards": [...] } |
sw.js |
Service Worker(離線快取 + 推播顯示) | 改任何快取檔就把 CACHE 版號 +1 |
manifest.json |
PWA 安裝資訊 | |
assets/*.png |
帶圖題的圖 | |
tools/sources.json tools/extract.sh |
官方試題來源清單 + 抽文字腳本 | 加新梯次用 |
worker/ |
Cloudflare Worker:同步 + 推播 + cron | 要自架後端才需動 |
題庫 schema(questions.json)
{
"meta": {
"title": "...",
"note": "...",
"defaultTimeLimitMin": 90,
"guides": { "科目1:人工智慧基礎概論": "<學習指引PDF網址>", ... }
},
"questions": [
{
"id": "115-1-b-s1-q3", // 唯一;慣例 <梯次>-<b初級/m中級>-s<科>-q<N>;帶圖題用 -f<N>
"level": "初級", // 初級 / 中級
"round": "115年第一次",
"subject": "科目1:人工智慧基礎概論",
"chapter": "機器學習", // 練習「範圍」依此分組;沒填會退回用 subject
"topic": "監督式學習", // 細標籤(自由),關鍵字搜尋會吃到
"question": "題幹…",
"options": ["A選項", "B選項", "C選項", "D選項"], // 必須剛好 4 個
"answer": 2, // 正解的 0-based 索引:A=0 B=1 C=2 D=3
"explanation": "詳解…", // 為何對 + 為何其他錯 + 概念
"image": "assets/<id>.webp", // 選填:帶圖題才有,檔名一律 = 題目 id(WebP lossless)
"source": "學習指引" // 選填:來源。缺省=歷屆考古題;"學習指引"=官方學習指引範例題(id 以 lg- 開頭、答案與解析皆官方)
}
]
}
加題目最小步驟:把新物件 append 進 questions.questions,確認 options 4 個、answer 是 0-3、id 不重複,然後:
node -e "JSON.parse(require('fs').readFileSync('questions.json'))" # 驗 JSON 合法
node core.test.mjs # 驗邏輯沒壞
python3 -m http.server 8000 # 開 http://localhost:8000 看
chapter請沿用既有的(統計頁/範圍選單會自動多出該組);不填則以subject當範圍。- 帶圖題:圖放
assets/,檔名一律命名為<題目 id>.webp(WebP lossless,例如assets/114-2-m-s3-f1.webp),image欄填assets/<id>.webp。看 id 就知道圖、看圖就知道哪題,別沿用原始 PDF 的圖片序號(早期 114-2 沒這樣做,踩過坑)。不要把含「答案欄」的整頁截圖放進去(會洩答案)——只放圖本身。 - 題幹若寫「附圖/如圖/下圖」就一定要有
image(歷史教訓:q39 抽圖時漏掛,題目變成無法判讀)。加完用node tools/check-questions.mjs驗。
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.
- 8d ago First seen · 134 lines · 2,897 tokens per session scan A 2c5a16554a6d
ipas-ai-quiz AGENTS.md is an instructions file published in the GitHub repository yazelin/ipas-ai-quiz (24 stars, last pushed yesterday), licensed MIT. It adds 2,897 tokens to every session, about $0.0145 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.