Cost Benchmark
技能 已验证 活跃Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table
To provide a verifiable, local benchmark for LLM cost performance, ensuring accuracy in claimed costs and facilitating performance audits.
功能
- Run local corpus benchmark
- Support optional Gemini/Sonnet/Opus baselines
- Persist verifiable measured-vs-claimed table
- Documented environment overrides for customization
- Output historical and latest benchmark runs
使用场景
- Verify release cost claims before publishing
- Confirm new benchmark cases route correctly
- Audit 'claimed upstream' tags by verifying benchmark support
- Compare costs of different LLM models for specific tasks
非目标
- Modifying benchmark corpus data
- Running benchmarks against live production systems
- Automated remediation of cost regressions
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
Janitor Tokens
100显示每个技能消耗的上下文窗口令牌数量。当用户询问有关令牌成本、上下文预算、技能大小，或希望了解哪些技能浪费了最多的上下文空间时使用。
Cloud Architect
100Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost optimization, disaster recovery, landing zones, security architecture, serverless design.
Chat Format
100Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
Wrap Up Ritual
100End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.
Project Development
100This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.