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.
git clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimizedWrote 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/rules/mr-chen-05/rules-2.1-optimized/performance-monitoring-system)<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/performance-monitoring-system"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/performance-monitoring-system/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/rules/mr-chen-05/rules-2.1-optimized/performance-monitoring-system"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/performance-monitoring-system.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 | $0.03555 | $0.03555 |
| Opus 5 | $0.01777 | $0.01777 |
| Sonnet 5 | $0.00711 | $0.00711 |
| Haiku 4.5 | $0.00356 | $0.00356 |
Grade A, and why
performance-monitoring-system 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 10d 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 — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📈 性能监控系统
实时洞察: 全面监控系统性能，识别瓶颈，优化用户体验，确保系统高效运行。
一、监控维度
1.1 响应时间监控
用户请求响应: 首次响应时间: - 目标: <2秒 - 测量点: 用户输入完成 → AI首次输出 - 监控频率: 每次请求 - 异常阈值: >5秒
完整响应时间: - 目标: 简单查询<5秒, 复杂任务<30秒 - 测量点: 请求开始 → 任务完成 - 监控频率: 每次请求 - 异常阈值: >2倍预期时间
工具调用性能: MCP工具执行: - 文件读取: <500ms - 文件写入: <1秒 - 目录操作: <200ms - GitHub API: <3秒 - Memory操作: <1秒
超时检测: - 轻度超时: >2倍正常时间 - 严重超时: >5倍正常时间 - 超时处理: 自动重试或降级
文件操作性能: 读取性能: - 小文件(<1MB): <100ms - 中文件(1-10MB): <500ms - 大文件(>10MB): 分块读取
写入性能: - 追加操作: <200ms - 完整写入: <500ms - 批量操作: <2秒
任务完成时间: 按复杂度分类: - Level 1任务: <10秒 - Level 2任务: <30秒 - Level 3任务: <2分钟 - Level 4任务: <5分钟 - Level 5任务: <15分钟
1.2 资源使用监控
内存占用: 正常范围: - 空闲状态: <100MB - 轻度使用: <300MB - 中度使用: <500MB - 重度使用: <1GB
监控指标: - 当前内存使用 - 内存使用峰值 - 内存增长率 - 内存泄漏检测
告警阈值: - 警告: >800MB - 严重: >1.5GB - 危险: >2GB
CPU使用率: 正常范围: - 空闲状态: <10% - 思考状态: 20-40% - 工具调用: 30-60% - 密集计算: 60-80%
监控指标: - 当前CPU使用率 - CPU使用峰值 - 平均CPU使用率 - CPU使用时长
告警阈值: - 警告: 持续>70%超过30秒 - 严重: 持续>90%超过10秒
磁盘IO: 读取性能: - 正常: <50MB/s - 峰值: <100MB/s - 监控: 读取次数和总量
写入性能: - 正常: <30MB/s - 峰值: <80MB/s - 监控: 写入次数和总量
IO等待: - 正常: <5% - 警告: >15% - 严重: >30%
网络请求: 请求统计: - API调用次数 - 请求成功率 - 平均响应时间 - 带宽使用
异常监控: - 连接超时 - 请求失败率 - 重试次数 - 限流触发
1.3 系统指标监控
工具调用统计: 成功率监控: - 目标: >99% - 监控: 成功/失败/超时 - 分类统计: 按工具类型分组
失败分析: - 失败原因分类 - 失败频率趋势 - 失败影响范围 - 自动修复尝试
错误频率: 错误分级: - 致命错误: 立即告警 - 严重错误: 记录并通知 - 一般错误: 记录日志 - 警告信息: 定期汇总
频率监控: - 每小时错误数 - 错误率趋势 - 错误类型分布 - 错误恢复率
重试机制: 重试统计: - 重试次数 - 重试成功率 - 平均重试时间 - 最终失败率
优化建议: - 高重试率操作识别 - 重试策略调整 - 超时阈值优化
缓存性能: 命中率统计: - L1缓存: 目标>90% - L2缓存: 目标>80% - L3缓存: 目标>70%
性能指标: - 缓存读取时间 - 缓存更新时间 - 缓存失效频率 - 缓存大小控制
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.
- 10d ago First seen · 533 lines · 3,555 tokens per session scan A 0089e77d3958
performance-monitoring-system is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (173 stars, last pushed 10mo ago), licensed MIT. It adds 3,555 tokens to every session, about $0.0178 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.