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 voidvec/drogon-claude-plugin --skill drogon-gen-websocketgit clone --depth 1 https://github.com/voidvec/drogon-claude-pluginWrote 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/voidvec/drogon-claude-plugin/drogon-gen-websocket)<a href="https://agentmods.dev/skills/voidvec/drogon-claude-plugin/drogon-gen-websocket"><img src="https://agentmods.dev/badge/skills/voidvec/drogon-claude-plugin/drogon-gen-websocket/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/voidvec/drogon-claude-plugin/drogon-gen-websocket"><img src="https://agentmods.dev/badge/skills/voidvec/drogon-claude-plugin/drogon-gen-websocket.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 | $0.00039 | $0.00547 |
| Opus 5.5 | $0.00016 | $0.00219 |
| Sonnet 5.5 | $0.00008 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
drogon-gen-websocket 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 21d 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.
What it actually says
drogon-gen-websocket
生成 drogon WebSocket 长连接服务端代码（客户端简述）。
使用场景
当需要服务端主动推送、聊天室广播、双向实时通信（IM/行情/协同）或 per-连接状态管理时使用。宏与方法签名均对照 v1.9.13 源码核对；A/B 组纪律（不阻塞事件循环、跨循环共享状态加锁）在 WS 同样适用。
输入参数
scene: 业务场景——chat（聊天室/房间）/push（服务端推送）/duplex（双向通信）path: WS 路由（如/chat；WS_PATH_ADD不加类名前缀）broadcast: 是否需要广播（默认false；true用PubSubService模板）state: 连接状态存储——context（默认，per-连接）/map（userId→conn 注册表，需加锁）client: 是否附带客户端示例（默认false）heartbeat: 心跳间隔（可选；框架默认 30 秒自动 ping，一般不改）
输出
WebSocketController<T>完整骨架：handleNewConnection/handleNewMessage/handleConnectionClosed+WS_PATH_LIST_BEGIN/WS_PATH_ADD/WS_PATH_LIST_END宏注册- 连接状态绑定（
setContext存 userId 等）与广播实现（PubSubService或加锁连接表） - 消息类型分支（Text/Binary/Ping/Pong/Close）与心跳说明
- 可选：
WebSocketClient::newWebSocketClient客户端最小示例
示例
/drogon-gen-websocket scene=chat path=/chat broadcast=true
/drogon-gen-websocket scene=push path=/ws state=map client=true
参考文件
详细实现指南见 references/code-guide.md（含参数验证、控制器骨架、连接管理/广播、消息收发、禁止模式清单）。生成代码前先读取该文件。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago Changed 822ed0e93055
- 24d ago First seen · 41 lines · 39 tokens per session scan A 0da5e0fbc820
drogon-gen-websocket is a skill published in the GitHub repository voidvec/drogon-claude-plugin (1 stars, last pushed 19d ago), licensed MIT. It adds 39 tokens to every session and 547 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-22.
Other skills, from other repositories
backend-standards
CMDO architecture standards for Node.js/TypeScript backends with strict layer separation.
backend-scaffolding
Scaffolds Node.js/TypeScript backend components with CMDO architecture, driven by component settings.
contract-standards
OpenAPI contract standards for API specification, versioning, and type generation.
contract-scaffolding
Scaffolds OpenAPI contract component with type generation.
Async Correctness 非同期処理の正しさ検証
A code review check for asynchronous code, meaning work that finishes later through async/await, promises, or chained callbacks. It looks for missing waits, ignored errors, and operations that can run in the wrong order or interfere with each other.
optimize
Audits and optimizes frontend, backend, and perceived performance against PRD budgets. This skill should be used when the user asks to "optimize performance", "run a performance audit", "improve page speed", "check Lighthouse scores", "fix Core Web Vitals", "reduce bundle size", "optimize queries", or "improve loading…