Can I export these metrics for external reporting?

Yes, by setting the format parameter to 'json', you can receive raw data suitable for integration with other monitoring tools or dashboards.

How do I use these metrics to improve performance?

Review the 'Recommendations' section in the output, which suggests actions like enabling compression or clearing expired documents based on your current hit rate and storage usage.

What specifically does this skill measure?

It measures cache hit rates, average fetch times versus cache hit times, total storage size, document freshness percentages, and specific source breakdowns.

Does analyzing the cache impact my existing data?

No, this is a read-only operation. It analyzes the cache index and metadata to generate statistics without modifying or deleting any of your stored data.

Codex Cache Metrics

Name: Codex Cache Metrics
Author: fractary

byfractary

•

Analytics & Monitoring

Analyzes knowledge retrieval performance, storage usage, and health status for the Fractary Codex plugin.

About

The Codex Cache Metrics skill provides deep visibility into your AI knowledge retrieval infrastructure by generating detailed statistics on cache efficiency and storage health. It enables developers to monitor cache hit rates, track fetch latency, and identify storage bottlenecks by delegating directly to the Fractary CLI. Whether you need a high-level health check or a granular breakdown of document freshness across various sources, this skill offers the actionable insights needed to optimize your Claude Code development environment.

Key Features

Automated health diagnostics for cache accessibility and index integrity
Comprehensive performance tracking including cache hit/miss ratios and fetch latency
Source-specific metrics to monitor data freshness and TTL status per provider
Granular storage analysis with document size breakdowns and growth rate projections
Actionable optimization recommendations for storage management and performance tuning
2 GitHub stars

Use Cases

Optimizing retrieval speed by identifying and resolving low cache hit rates
Managing disk space by auditing large cached documents and expired entries
Troubleshooting knowledge retrieval failures through automated health and status checks

About

Key Features

Automated health diagnostics for cache accessibility and index integrity
Comprehensive performance tracking including cache hit/miss ratios and fetch latency
Source-specific metrics to monitor data freshness and TTL status per provider
Granular storage analysis with document size breakdowns and growth rate projections
Actionable optimization recommendations for storage management and performance tuning
2 GitHub stars

Use Cases

Optimizing retrieval speed by identifying and resolving low cache hit rates
Managing disk space by auditing large cached documents and expired entries
Troubleshooting knowledge retrieval failures through automated health and status checks