How does this skill access my usage data?

It reads local files stored in ~/.omc/state/ and .claude/ on your machine, ensuring your usage metrics and patterns stay private.

Can it help me save money on API costs?

Yes, it specifically identifies high-cost Opus usage and suggests switching to Ecomode or Haiku for routine tasks to reduce token consumption.

Do I need to set anything up to use this skill?

No special setup is required; however, the more you use OMC, the more accurate and personalized the recommendations will become.

What happens if I have no session history?

The skill will provide a 'Limited Usage Data' report and provide tips on how to enable tracking and configure your OMC environment for the first time.

OMC Usage Insights

Name: OMC Usage Insights
Author: Yeachan-Heo

byYeachan-Heo

•

4,261

分析与监控

Analyzes your Oh My Claude Code (OMC) usage patterns to provide personalized workflow optimizations and token-saving recommendations.

关于

The learn-about-omc skill serves as an intelligent auditor for your Claude Code environment, parsing local session histories and token tracking logs to reveal how you interact with different agents and models. By identifying underutilized execution modes like Ecomode or Pipeline and quantifying your model distribution, it delivers actionable insights to reduce costs and enhance development speed. Whether you're looking to optimize your spend on Claude 3 Opus or streamline multi-agent workflows, this skill provides the data-driven roadmap needed to master the OMC ecosystem.

主要功能

Graceful degradation for systems with limited historical data
Agent popularity tracking and usage frequency reports
Token usage analysis by model (Opus, Sonnet, Haiku)
Automated identification of underutilized OMC execution modes
Personalized configuration recommendations for better efficiency
4,261 GitHub stars

使用场景

Configuring OMC settings based on actual historical usage data
Auditing AI token spend and identifying expensive model usage patterns
Optimizing developer workflows by discovering relevant multi-agent modes

关于

主要功能

Graceful degradation for systems with limited historical data
Agent popularity tracking and usage frequency reports
Token usage analysis by model (Opus, Sonnet, Haiku)
Automated identification of underutilized OMC execution modes
Personalized configuration recommendations for better efficiency
4,261 GitHub stars

使用场景

Configuring OMC settings based on actual historical usage data
Auditing AI token spend and identifying expensive model usage patterns
Optimizing developer workflows by discovering relevant multi-agent modes