Skip to main content

Cost Benchmark

Skill Verified Active

Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table

Purpose

To provide a verifiable, local benchmark for LLM cost performance, ensuring accuracy in claimed costs and facilitating performance audits.

Features

  • 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

Use Cases

  • 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

Non-Goals

  • Modifying benchmark corpus data
  • Running benchmarks against live production systems
  • Automated remediation of cost regressions

Installation

First, add the marketplace

/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-cost-tracker@ruflo

Quality Score

Verified
99 /100
Analyzed about 16 hours ago

Trust Signals

Last commitabout 17 hours ago
Stars50.2k
LicenseMIT
Status
View Source

Similar Extensions

© 2025 SkillRepo · Find the right skill, skip the noise.