Cost Trend
技能 已验证 活跃Read every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over time
To proactively identify performance and cost regressions in AI model benchmarks before they impact releases or production environments.
功能
- Analyzes benchmark run history
- Surfaces drift in win rate, latency, and cost
- Flags performance regressions
- Supports JSON output for further processing
使用场景
- Before a release to check for performance regressions.
- After corpus expansion to verify older runs still perform well.
- After upgrading agent frameworks to identify latency or strategy changes.
非目标
- Running benchmarks; it only analyzes existing results.
- Detecting regressions not captured in the `*.json` files.
- Providing real-time monitoring; it's for historical analysis.
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-cost-tracker@ruflo质量评分
已验证类似扩展
Benchmark
100Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". (gstack) Voice triggers (speech-to-text aliases): "speed test", "check performance".
V3 Performance Engineer
99Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer
Agent Benchmark Suite
99Agent skill for benchmark-suite - invoke with $agent-benchmark-suite
Social Media Analyzer
100Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use for analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards.
Ops Revenue
100Revenue and costs tracker. AWS spend via aws ce, credits tracker, project revenue stages. Shows burn rate, runway estimate, credits expiring.
Usage Tracker
100跟踪每次本地 Claude Code 使用情况并进行报告：消耗的 token 数、预估成本（欧元）、会话数、项目数以及工具细分。当用户询问有关消耗、积分、使用情况、每次请求的成本、想要查看报告、询问特定请求为何昂贵、怀疑某个进程正在消耗 token、想要优化 Claude Code 使用情况或想要审核每次请求的工具使用情况时使用。还会触发对西班牙语短语的响应：'cuánto me está costando', 'cuántos tokens', 'consumo de hoy', 'qué petición fue cara', 'está consumiendo mucho', 'optimizar consumo', 'reporte de uso', 'ver uso', 'instalar tracker', 'hook no registra'。命令：/usage-tracker report [hoy|semana|mes|all] [proyecto], /usage-tracker top-requests [hoy|semana], /usage-tracker install, /usage-tracker status