cercano-stats

Analyze Cercano usage telemetry to quantify local versus cloud inference and token savings.

8|1|Updated Nov 23, 2025

Search Tags:#analytics #telemetry #usage #token-savings #local-inference #cloud-inference #cercano

Ready to run

npx skills add https://github.com/bryancostanich/Cercano --skill cercano-stats

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cercano-stats
Source: https://github.com/bryancostanich/Cercano/tree/main/plugins/skills/cercano-stats
Command: npx skills add https://github.com/bryancostanich/Cercano --skill cercano-stats

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quantify Cercano usage and token savings by comparing local inference against cloud-assisted options.

Core Features & Use Cases

Usage telemetry: shows total requests, local tokens, and cloud tokens (when reported), plus kept local percentage.
Breakdowns: provides per-tool and per-model breakdowns, with recent activity over the last 7 days.

Quick Start

Ask Cercano stats to generate a 7-day usage report.

Frequently Asked Questions about cercano-stats

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I track local versus cloud inference usage and token savings?▼

You can quantify local versus cloud inference usage by analyzing telemetry data for total requests, local tokens, cloud tokens, and the kept local percentage, providing a clear view of token savings.

Can I break down inference usage telemetry by tool and model?▼

Yes, you can break down inference usage telemetry by tool and model. The analysis provides per-tool and per-model breakdowns to help you understand exactly where local and cloud tokens are being consumed.

How do I generate a 7-day usage report for local and cloud inference?▼

To generate a 7-day usage report for local and cloud inference, request a recent activity analysis. It summarizes total requests and token breakdowns over the last 7 days for your tools and models.

What is the kept local percentage in inference usage analytics?▼

The kept local percentage in inference usage analytics measures the proportion of processing handled locally rather than in the cloud, calculated by comparing local token counts against total token usage.

Does this usage telemetry analysis report cloud token consumption?▼

Yes, the usage telemetry analysis reports cloud token consumption when available. It compares local inference against cloud-assisted options to quantify total requests and overall token savings.