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 xcodethink/open-claude-code-skills --skill 12git clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWrote 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/xcodethink/open-claude-code-skills/12)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/12"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/12/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/xcodethink/open-claude-code-skills/12"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/12.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 | $0.00278 | $0.02888 |
| Opus 5.5 | $0.00111 | $0.01155 |
| Sonnet 5.5 | $0.00056 | $0.00578 |
| Haiku 4.5 | $0.00028 | $0.00289 |
Grade A, and why
12-系统监控和告警 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 1mo 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
系统监控和告警标准
核心原则：系统出了问题，必须在 1 分钟内通知到人。不允许系统静默故障。
两层架构
这个 skill 提供两层监控能力,按项目阶段递进接入:
Tier 1 — 基础层 (本文件)
所有项目必须接入。最少要做的事:Lark webhook + 健康检查端点 + 结构化日志 + 审计日志。
Tier 2 — 商业级层 (incident-management/)
有付费用户、有 SLA、有 cron 任务的项目必须接入。在 Tier 1 之上提供:
- 事件状态机(firing → acked → snoozed → resolved)
- Fingerprint 去重 + N-of-M 跨周期去抖(消除 99% 误报)
- 3 级自动升级(15min/60min/4h)
- 自愈 [RESOLVED] 闭环通知(终结"狼来了")
- 实时 SLO 仪表盘(uptime / MTTR / MTBF)
- Cron lag 检测(safety net)
- 第三方 provider 监控
- Ack / Snooze 工作流(管理员可在 admin Tab 点击操作)
11 个可复制的代码模板 + 完整接入手册 + 经验教训 + 验收清单都在 incident-management/ 子目录。第一次接入耗时 2 小时,熟练后 30 分钟。
何时升级到 Tier 2?
- 项目已上线生产
- 有付费用户
- 依赖 ≥ 3 个第三方 API
- 有 cron 任务
- 需要回答客户"你们 uptime 多少"
满足任何一条 → 立即接入 Tier 2,详见 incident-management/INSTALL.md。
详细规范（详细规范/）
本 SKILL.md 是入口和 Tier 1 基础接入。完整规范在 详细规范/ 下，需要深入时按需读取：
详细规范/监控告警.md— 全链路 4 层监控架构、8 项必监控环节、告警格式模板（Telegram/Lark/WhatsApp）、每日业务报告、健康检查端点（标准版+Prisma 版）、前端 AI 请求兜底、监控实施步骤、Cloudflare 专属监控详细规范/可观测性规范.md— 可观测性三支柱（Metrics / Logs / Traces）、SLO/SLI 定义、告警分级与降噪、Cloudflare Analytics Engine、结构化日志、分布式追踪详细规范/事件管理规范.md— 事件严重度定义（P0-P3）、响应 SLA、事件响应流程、沟通模板、事后复盘（5 Whys）、常见事件剧本详细规范/系统埋点与告警集成标准.md— 埋点分类与标准、告警通道集成代码模板、必须告警的场景、环境变量标准、每日业务报告集成
1. Lark 飞书机器人告警（必须接入）
1.1 架构
应用代码 → AlertService → Lark Webhook → 飞书群消息
1.2 告警级别
| 级别 | 颜色 | 触发条件 | 示例 |
|---|---|---|---|
| [CRITICAL] | 红色 | 系统不可用、数据丢失 | 数据库连接失败、认证服务崩溃 |
| [ERROR] | 橙色 | 功能异常但系统可用 | API 请求 5xx、第三方 API 失败 |
| [WARNING] | 黄色 | 需关注但不紧急 | 高延迟、API 配额接近上限 |
| [INFO] | 蓝色 | 重要业务事件 | 用户注册、大批量操作完成 |
1.3 标准实现
sendAlert(payload) 接受 AlertPayload（level / title / details / project / environment / timestamp / requestId? / userId? / extra?），内部用 LARK_WEBHOOK_URL env 推送 Lark 卡片消息。告警服务本身不能阻断主流程（catch 后只 console.error）。
What ships with it
25 files 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.
- _ref/代码模板.md 6.4 KB
- agents/openai.yaml 927 B
- incident-management/ARCHITECTURE.md 14 KB
- incident-management/checklist.md 8.6 KB
- incident-management/INSTALL.md 12 KB
- incident-management/lessons-learned.md 18 KB
- incident-management/README.md 5.7 KB
- incident-management/templates/adminApi.snippet.ts 3.6 KB runs code
- incident-management/templates/aiQuotaGuard.ts.template 13 KB
- incident-management/templates/cronLagMonitor.ts.template 7.6 KB
- incident-management/templates/healthMonitor.ts.template 15 KB
- incident-management/templates/healthNotifier.ts.template 21 KB
- incident-management/templates/incidentManager.ts.template 26 KB
- incident-management/templates/index_routes.snippet.ts 4.9 KB runs code
- incident-management/templates/migration_incident_management.sql.template 3.7 KB
- incident-management/templates/operationAlert.ts.template 7.8 KB
- incident-management/templates/providerHealthMonitor.ts.template 6.8 KB
- incident-management/templates/sloAdmin.ts.template 6.4 KB
- incident-management/templates/sloMetrics.ts.template 14 KB
- incident-management/templates/SloTab.tsx.template 18 KB
- SKILL.en.md 9.9 KB
- 详细规范/事件管理规范.md 8.3 KB
- 详细规范/可观测性规范.md 13 KB
- 详细规范/监控告警.md 15 KB
- 详细规范/系统埋点与告警集成标准.md 17 KB
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.
- 1mo ago First seen · 206 lines · 278 tokens per session scan A d02d5d2360fe
12-系统监控和告警 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 278 tokens to every session and 2,888 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
flutter-idioms
Flutter idioms: Riverpod 3 state management, Freezed immutable models, gorouter navigation, const widget optimization, and repository patterns. Use when developing, refactoring, or reviewing Flutter mobile applications.
go-idioms
Go idioms and patterns: stdlib conventions, explicit error wrapping (%w), small interfaces, goroutines/channels concurrency, table-driven tests, and gofumpt formatting. Use when writing, refactoring, or reviewing Go services and packages.
rust-idioms
Rust idioms: ownership and borrow checker patterns, error handling with thiserror/anyhow, Tokio async concurrency, lifetime management, and Clippy pedantic compliance. Use when writing, optimizing, or reviewing Rust crates.
typescript-idioms
TypeScript strict typing: type narrowing, discriminated unions, Zod runtime validation, generic utility types, and Vitest testing. Use when writing or refactoring TypeScript across frontend, backend, or full-stack projects.
vue-idioms
Vue 3 Composition API patterns: syntax, reactive state with Pinia stores, reusable composables, and Vitest component testing. Use when developing or refactoring Vue 3 frontend applications.
axum-idioms
Axum (0.8+) web framework patterns: type-safe extractors, Tower middleware, route routing, and graceful shutdown. Use when implementing HTTP APIs or web services in Rust. Pair with rust-idioms.