GoogleDevRelExplorations/cercano-stats
.claude/skills/cercano-stats/SKILL.md
View Cercano usage statistics and cloud token savings. Shows total requests, tokens processed locally, cloud tokens reported by the host, percentage kept local, and breakdowns by tool, model, and day.
tools
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add GoogleDevRelExplorations/cercano cercano-statsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 29, 2026, 4:22 PM12.7s1 file scanned
SKILL.md
- name:
- cercano-stats
- description:
- View Cercano usage statistics and cloud token savings. Shows total requests, tokens processed locally, cloud tokens reported by the host, percentage kept local, and breakdowns by tool, model, and day.
- compatibility:
- Requires Cercano server running with telemetry enabled.
Cercano Stats
View usage statistics and cloud token savings from Cercano's local inference.
MCP Tool
Tool name: cercano_stats
Parameters
No parameters required.
Output
Returns a markdown-formatted report including:
- Total requests processed locally
- Local tokens (input + output)
- Cloud tokens (if host-reported via
cercano_submit_usage) - Kept local percentage (when cloud data is available)
- Estimated cloud tokens saved (when no cloud data reported)
- Breakdown by tool (e.g. summarize, extract, classify)
- Breakdown by model (e.g. qwen3-coder, gemma3:4b)
- Recent activity (last 7 days)
Examples
Get usage stats:
{}
Sample output:
## Cercano Usage Statistics
**Total requests:** 42
**Local tokens:** 18,500 (15,200 in, 3,300 out)
**Estimated cloud tokens saved:** 18,500
### By Tool
- cercano_summarize: 20 calls, 12,000 tokens
- cercano_extract: 15 calls, 4,500 tokens
- cercano_classify: 7 calls, 2,000 tokens
### By Model
- qwen3-coder: 42 calls, 18,500 tokens
### Recent Activity
- 2026-03-24: 12 calls, 5,200 tokens
- 2026-03-23: 30 calls, 13,300 tokens
Related Skills
GoogleDevRelExplorations/cercano-summarize
devops
VerifiedTrustedCommunity
Summarize text or files using local AI via Cercano without sending content to the cloud. Supports brief, medium, and detailed summary lengths.
SKILL.mdUpdated Apr 16, 2026
GoogleDevRelExplorations/cercano-submit-usage
devops
VerifiedTrustedCommunity
Submit cloud token usage data to Cercano (opt-in). This sends data, not a report — use cercano_stats to view usage. Helps track cloud tokens alongside local inference for accurate local-vs-cloud comparison.
SKILL.mdUpdated Apr 16, 2026
GoogleDevRelExplorations/cercano-research
development
VerifiedTrustedCommunity
Research a question using DuckDuckGo search and local AI analysis. Crafts search queries, fetches top results, and synthesizes a sourced answer — all locally.
SKILL.mdUpdated Apr 16, 2026
GoogleDevRelExplorations/cercano-models
data-ai
VerifiedTrustedCommunity
List AI models available on the Ollama instance connected to Cercano. Returns model names, sizes, and modification dates. Use this to discover what local models are available before choosing one for inference or switching the active model.
SKILL.mdUpdated Apr 16, 2026