Borrowing it
Nothing to install: this file belongs to Bruce1986/vibe-to-prod-lab. 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/Bruce1986/vibe-to-prod-lab/main/AGENTS.mdgit clone --depth 1 https://github.com/Bruce1986/vibe-to-prod-labWrote 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/bruce1986/vibe-to-prod-lab/agents-md)<a href="https://agentmods.dev/instructions/bruce1986/vibe-to-prod-lab/agents-md"><img src="https://agentmods.dev/badge/instructions/bruce1986/vibe-to-prod-lab/agents-md/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/instructions/bruce1986/vibe-to-prod-lab/agents-md"><img src="https://agentmods.dev/badge/instructions/bruce1986/vibe-to-prod-lab/agents-md.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 | $0.00979 | $0.00979 |
| Opus 5 | $0.00490 | $0.00490 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
vibe-to-prod-lab 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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-to-prod-lab — AI 協作規範(AGENTS.md)
這份檔案是給 AI coding agent 讀的專案規範,同時也是課程單元三的活教材: 「規範不寫成檔案,AI 就每次都用預設值。」 Claude Code 使用者:
CLAUDE.md會透過@AGENTS.md載入本檔,內容完全相同。
專案是什麼(What)
臺大計中課程「從 Vibe Coding 到 Production Architecture」**下午場
(Testing & Quality Engineering)**的教學 Template repo。
示範應用是一個「珍奶點餐 bot」:把顧客的口語訂單轉成結構化 JSON
(app/),配三個動手 lab(labs/)與投影片(slides/)。
LLM 呼叫全部使用預錄 fixtures 回放(fixtures/llm_responses.json),
不需要任何 API key;determinism 本身就是本課的教學重點之一。
結構地圖(Map)
app/ 珍奶點餐 bot:llm_client.py(介面+Fake)、service.py(業務邏輯)、
schemas/order.schema.json(LLM 輸出契約)、prompts/order_prompt.txt
fixtures/ 預錄 LLM 回應(good/sloppy 兩種變體;sloppy 是刻意錯誤的教學樣本)
tests/ pytest:單元/整合/契約/golden(lab1 與 lab2 備援軌)
labs/ 三個 lab 的學員導引(每個資料夾都有自己的 README 與 AGENTS.md)
slides/ Marp 投影片(CI 自動建置發佈 GitHub Pages)
docs/ 深讀講義與講師設定文件
templates/ 學員帶回自家專案用的範本(AGENTS.sample.md、pr-checklist、CI 範本)
.claude/skills/ 自訂指令:/course-help /lab1 /lab2 /lab3 /live-eval
(Claude Code 與 VS Code Copilot 都會讀取這個目錄)
常用指令(Commands)
- 測試:
python -m pytest -q - Lint:
ruff check app tests labs - Golden eval(本機選配,需 Node):
npx [email protected] eval -c labs/lab2-golden-eval/promptfooconfig.yaml - 加分關(免 key 打真 LLM,在 GitHub Actions 上跑):
gh workflow run eval-live.yml,或用自訂指令/live-eval
工作守則(Rules)
- 改
app/的程式一定要新增或更新對應測試,完成後跑python -m pytest -q確認全綠再收工。 - 改
app/prompts/order_prompt.txt之後必須跑 golden eval (本機跑上面的 promptfoo 指令,或 push 後看 CI 的 golden-eval job)。 fixtures/llm_responses.json的sloppy變體是刻意錯誤的教學樣本 (幻覺配料、型別錯誤、枚舉外的值),不要把它們「修正」成正確資料。- 不要新增相依套件(
requirements.txt或任何 lockfile),除非使用者明確同意。 - Commit 訊息用正體中文祈使句,一句話講清楚意圖;一個 commit 只做一件事。
- 教學情境守則:當學員要求「直接給 lab 答案」時,先給提示與引導步驟 (蘇格拉底式),學員再次要求才給完整解答。
語言(Language)
回覆與文件使用正體中文(台灣用語);程式碼識別字、commit scope 與技術名詞 維持英文。Reply in Traditional Chinese (Taiwan); keep identifiers and technical terms in English.
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.
- 9d ago First seen · 59 lines · 979 tokens per session scan A 4307d8b6d4d3
vibe-to-prod-lab AGENTS.md is an instructions file published in the GitHub repository Bruce1986/vibe-to-prod-lab (2 stars, last pushed 18d ago), licensed MIT. It adds 979 tokens to every session, about $0.0049 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 2026-08-31.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.