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/whyiyhw/agentcard/agentcard-deploynpx skills add whyiyhw/agentcard --skill agentcard-deploygit clone --depth 1 https://github.com/whyiyhw/agentcardWrote 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/whyiyhw/agentcard/agentcard-deploy)<a href="https://agentmods.dev/skills/whyiyhw/agentcard/agentcard-deploy"><img src="https://agentmods.dev/badge/skills/whyiyhw/agentcard/agentcard-deploy.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 | $0.00148 | $0.02946 |
| Opus 5 | $0.00074 | $0.01473 |
| Sonnet 5 | $0.00030 | $0.00589 |
| Haiku 4.5 | $0.00015 | $0.00295 |
Grade B, and why
agentcard-deploy scanned grade B with 2 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 4d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- AI:站点里问一句,或 `curl -s https://<你的域名>/api -H 'content-type: application/json' -d '{"q":"介绍一下你自己","lang":"zh"}'`。 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `worker/config.js` —— 人设、事实基线、curl 名片、邮件模板、A2A 卡(**全部个人内容在这**) How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentcard-deploy — 带 fork 者把这张 AI 名片变成他自己的
一句话:这不是一张静态简历页,是一张会替主人接待、筛选、转化访客的 AI 终端名片。访客来了,它自我介绍、回答问题、识别是不是有合作意向、捕获线索并通知主人。这个 skill 带用户把 demo 里的内容换成他自己的,并把后端配起来。
This is not a static résumé page — it's an AI business card that greets, screens, and converts visitors on the owner's behalf. This skill walks a forker through replacing the demo content and wiring up the backend.
给 AI 的执行原则: 一步步来,每一步做完让用户确认再往下。不要用占位符批量覆盖用户内容——先访谈,拿到用户的真实信息再写。命令一律在 worker/ 或仓库根目录跑,涉及 secret 的让用户自己执行(你不经手任何 key)。
0. 先说清楚这东西是什么、为什么这么设计(理念 + 安全模型)
部署前先让用户理解设计,不然改起来会踩坑:
定位。 北极星是「每月有效合作线索」。不是博客(内容)、不是求职页(投递),而是:展示品味 → 回答问题 → 识别合作意向 → 捕获线索。终端世界观本身自带传播点(访客会截图)。
安全是结构性的,不是靠 prompt 求模型「别说」。 这是整个项目最该被继承的部分:
- DeepSeek key 只存 Worker secret,永远不进前端。 前端放 key = 当场被扒出来盗刷。前端只调
AI_ENDPOINT,key 在ai-proxy.js里从env读。 - 微信号只在 secret
WECHAT_ID,经offer_wechat工具服务端门控发放。 明文不进 system prompt、不进页面——所以再怎么 prompt 注入也套不出来。门控:访客必须先留下自己的联系方式,服务端校验通过才返回;每会话最多放行 2 次。 - 完整简历
send_resume四重门控: 邮箱必须是访客亲手在对话里敲的(模型编不出没出现过的地址)· 同邮箱 7 天不重发 · 每会话 1 次 · 全局每日 ≤10。邮件是固定模板 = 零注入面;不做任何自由外发邮件。 - 隐私红线: IP 只存 SHA-256 截断哈希;完整简历 PDF 无手机号 / 无薪资 / 无微信号;直接访问
/resume.pdf无签名 token 一律 404。
内容 / 引擎分离(fork 的核心契约)。 你只需要改三处内容,引擎不用碰:
worker/config.js—— 人设、事实基线、curl 名片、邮件模板、A2A 卡(全部个人内容在这)index.html的 HTML 内容区 —— hero 文案、作品卡、能力、联系方式pdf-src/—— 简历 / 合作简介的 HTML 源,重出 PDFworker/ai-proxy.js是引擎,不用改(AI 代理 / 工具 / 落库 / 后台 / 通知 / A2A;所有对主人的引用都从config.js的SITE派生)。
A2A(差异点)。 别人的 agent 可以直接发现并询问你的名片:GET /.well-known/agent-card.json 发现 + POST /a2a(JSON-RPC message/send,带 contextId 自动多轮)。人不在场,两个 agent 先把匹配度聊完。
兜底。 AI 挂了 / 没配 key 时,ask 自动回退本地脚本应答,页面永不白屏。所有落库 / 通知都走 waitUntil 旁路,挂了不影响回答。
1. Preflight(环境 + 从模板起手)
node -v # 需要 Node 18+
npx wrangler --version
cd worker
cp wrangler.toml.example wrangler.toml # 真实配置(域名/Feishu/D1)在这里改,已被 gitignore
cp .dev.vars.example .dev.vars # 本地联调用,填你的 DEEPSEEK_API_KEY,已被 gitignore
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.
- 4d ago First seen · 146 lines · 148 tokens per session scan B 3147957fa9a0
agentcard-deploy is a skill published in the GitHub repository whyiyhw/agentcard (5 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 2,946 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
rule
Skill "rule" from x-cmd/x-cmd, covering rule — rules to rule, 核心命令, 规则文件格式, 示例 and 验证规则文件格式.
cve
Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.
azmon-mirroredcatalogs-operations-cli
Brings Azure Monitor, Application Insights, and Log Analytics telemetry into Fabric as Eventhouse external delta tables and correlates it with business data. Use to onboard observability data, judge whether latency or availability affected revenue, or build a Real-Time dashboard and Operations Agent over it.
atmos-auth
Authentication and identity management: providers (SSO/SAML/OIDC/GCP/Atmos Pro), identities, keyring, identity chaining, login/exec/shell/console, and github/sts for private GitHub access.
terraform-search-import
Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.