Borrowing it
Nothing to install: this file belongs to ai-cooperation/business-card-mcp. 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/ai-cooperation/business-card-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/ai-cooperation/business-card-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/instructions/ai-cooperation/business-card-mcp/agents-md)<a href="https://agentmods.dev/instructions/ai-cooperation/business-card-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ai-cooperation/business-card-mcp/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/ai-cooperation/business-card-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ai-cooperation/business-card-mcp/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 | $0.01386 | $0.01386 |
| Opus 5 | $0.00693 | $0.00693 |
| Sonnet 5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
business-card-mcp 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 11d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Business Card MCP 部署引導（跨 CLI）
你是導遊不是裁判：每一關綠燈由機械驗證判定。同一步驟失敗 3 次即停，記錄卡點。使用者確認不超過 3 次。
本專案為 SmallGreen Path A（原生採用）：契約三檔與本引導隨程式碼同 repo，無 adapter 層。
前置
- Node.js 20+、npm；
CLOUDFLARE_API_TOKEN＋CLOUDFLARE_ACCOUNT_ID（Workers＋D1＋R2＋KV Edit 權限） - 帳號需已啟用 R2（未啟用會在建 bucket 時 error 10042，僅 dashboard 可開）
- 網頁登入使用 Gmail OTP；不使用 Google OAuth 或 Cloudflare Zero Trust。Email Service 寄件網域需由 Cloudflare DNS 管理；寄送到帳號內 verified destination 可維持免費方案，任意收件者則依 Cloudflare Email Service 方案判定。
步驟
1. 說明與同意（確認 1）
讀 .smallgreen/profile.yaml 向使用者說明：名片與聯絡人資料存在自己帳號的 D1（結構化欄位與 markdown）、R2（私人縮圖）、KV（MCP key）；網頁 UI 用 allowlist 內的 Gmail OTP 登入，OTP challenge 與 session digest 存在自己的 D1；Turnstile 只作防濫用驗證，Email Service binding 只寄送驗證碼；名片辨識由 ChatGPT／Claude 端的視覺模型完成，本服務不呼叫任何模型 API。原始名片圖片不進 Worker，也不寫入 R2；Worker 只接收、驗證並保存模型端產生的 480px WebP 縮圖。
2. 組裝
git clone <本 repo> business-card-mcp && cd business-card-mcp
npm install
cp public/config.example.js public/config.js # 認證不需前端設定
wrangler.jsonc 已隨 repo 提供零值佔位版（SmallGreen SAP-1 需要可靜態判定的資源宣告）；下一步把真實 ID 填進去。填完建議 git update-index --skip-worktree wrangler.jsonc，避免真實 ID 被 commit。
3. 建立 Cloudflare 資源並填 ID
npx wrangler d1 create business-card-mcp
npx wrangler r2 bucket create business-card-mcp-assets
npx wrangler kv namespace create CARD_KEYS
把回傳的 D1 database_id、KV id 填入 wrangler.jsonc，並設定 vars：PUBLIC_BASE_URL、OTP_FROM_EMAIL、TURNSTILE_SITE_KEY 與 TURNSTILE_EXPECTED_HOSTNAME。先在 Email Service onboard 寄件網域，並確認 OTP 收件 Gmail 是 verified destination（或已啟用 Workers Paid）。接著設定 secrets：
npx wrangler secret put ALLOWED_GMAILS
npx wrangler secret put OTP_PEPPER
npx wrangler secret put TURNSTILE_SECRET_KEY
填完驗證設定可解析：
npx wrangler types && npm run typecheck
4. Migration、測試與部署（確認 2）
npm test
npx wrangler d1 migrations apply business-card-mcp --remote
npx wrangler deploy
5. 驗收（確認 3）
照 .smallgreen/acceptance.yaml：
GET /healthz→ 200- 以 allowlist 內的 Gmail 完成 Turnstile 與 OTP 登入後產生一把 MCP key，複製 Connector URL（URL 內含 key，視同密碼）
- 用該 key 呼叫
POST /mcp建立一筆已確認名片（請求格式見tests/fixtures/mcp-create-contact.valid.json） npx wrangler d1 execute business-card-mcp --remote --command "SELECT COUNT(*) FROM contacts"→ 該筆已寫入- 以姓名搜尋回得該筆；未登入直接開詳情頁應被擋（資料層 401，非頁面狀態碼）
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.
- 11d ago First seen · 86 lines · 1,386 tokens per session scan A 9787cc82ff0f
business-card-mcp AGENTS.md is an instructions file published in the GitHub repository ai-cooperation/business-card-mcp (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 1,386 tokens to every session, about $0.0069 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 2026-09-01.
Other instructions, from other repositories
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
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.
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).
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.