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 skills add EthanYoQ/Skill-hub --skill feishu-card-wsgit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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/ethanyoq/skill-hub/feishu-card-ws)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/feishu-card-ws"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/feishu-card-ws/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/skills/ethanyoq/skill-hub/feishu-card-ws"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/feishu-card-ws.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00150 | $0.03255 |
| Opus 5 | $0.00075 | $0.01628 |
| Sonnet 5 | $0.00030 | $0.00651 |
| Haiku 4.5 | $0.00015 | $0.00326 |
Grade A, and why
feishu-card-ws 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书卡片 WS 长连接配置指南
适用范围
本 skill 适用于使用 @larksuiteoapi/node-sdk 通过 WebSocket 长连接模式接收
飞书交互式卡片回调的场景。这套模式经过 2026-04-12 的实战验证,是目前唯一稳定可用的方案。
核心约束(先读这里)
Lark Node SDK v1.60.0 的 WSClient 有以下已确认的限制:
| 限制 | 影响 | 应对 |
|---|---|---|
| WSClient 不支持 CardActionHandler | start() 只接受 eventDispatcher 参数 |
用 EventDispatcher 注册 card.action.trigger |
| card 更新响应导致 200672 | { card: {...} } 经 base64 编码后飞书无法解析 |
所有操作只返回 toast |
| form_submit 按钮事件不到达 | action_type: "form_submit" 走不同协议路径 |
使用普通 button,服务端缓存 select 值 |
| monkey-patch handleEventData 破坏消息投递 | 干扰 SDK 内部分片合并逻辑 | 不要 monkey-patch |
架构总览
用户发关键词 → im.message.receive_v1 → EventDispatcher → 发送卡片
用户选下拉 → card.action.trigger(select_static) → 缓存值 → return undefined
用户点按钮 → card.action.trigger(button) → 注入缓存值 → 业务处理 → return toast
三种交互全部通过同一个 EventDispatcher 路由,不需要任何 SDK 扩展或 monkey-patch。
第一步:卡片模板
下拉菜单 + 按钮组合
// ✅ 正确:普通 button + select_static,不用 form 容器
{
tag: "select_static",
name: "my_select_key", // 用于服务端缓存的 key
placeholder: { tag: "plain_text", content: "请选择" },
value: { action: "my_select_key" }, // value.action 也用于识别
options: [
{ text: { tag: "plain_text", content: "选项1" }, value: "1" },
{ text: { tag: "plain_text", content: "选项2" }, value: "2" },
],
}
{
tag: "button",
name: "my_action_name", // 按钮名称
text: { tag: "plain_text", content: "🟢 执行操作" },
type: "primary",
value: { action: "my_action_name" }, // value.action 用于路由
}
独立按钮(无下拉)
{
tag: "button",
name: "my_simple_action",
text: { tag: "plain_text", content: "🔄 刷新" },
type: "default",
value: { action: "my_simple_action" },
}
反模式(不要这样做)
// ❌ form_container — form_submit 事件不通过 WS 到达
{ tag: "form", name: "myForm", elements: [select, { tag: "button", action_type: "form_submit" }] }
// ❌ action_type: "form_submit" — 事件完全不到达服务端
{ tag: "button", action_type: "form_submit", ... }
// ❌ 只靠 name 不设 value — 按钮的 action routing 依赖 value.action
{ tag: "button", name: "my_action" } // 缺少 value
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 · 344 lines · 150 tokens per session scan A 07b3081b4fa4
feishu-card-ws is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed 4d ago), licensed MIT. It adds 150 tokens to every session and 3,255 once invoked, about $0.0007 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 skills, from other repositories
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
detecting-api-enumeration-attacks
Detect and prevent API enumeration attacks including BOLA and IDOR exploitation by monitoring sequential identifier access patterns and authorization failures.
implementing-api-schema-validation-security
Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.
performing-api-inventory-and-discovery
Performs API inventory and discovery to identify all API endpoints in an organization's environment including documented, undocumented, shadow, zombie, and deprecated APIs. The tester uses passive traffic analysis, active scanning, DNS enumeration, JavaScript analysis, and cloud resource inventory to build a…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
api-debugging
Systematic approach to debugging REST APIs, HTTP errors, authentication issues, and network problems. Use when the user has API errors, status code issues, timeout problems, or needs help troubleshooting HTTP requests.