Claude Code emits OpenTelemetry metrics over OTLP. Anthropic publishes the metric names. So all that was missing, if you run a Prometheus-compatible backend, was a dashboard. Here is one.

Grafana Labs: dashboard 25255

Source: github.com/rockdarko/claude-code-metrics-prometheus

License: MIT

It's a port, not original work. The dashboard concept and panel set come from grafana.com 25052 by 1w2w3y , which targets Azure Application Insights via KQL. I rebuilt every panel in PromQL so the same view works against the OSS metrics stack. Credit upstream.

Why a port was worth doing

When my team started piloting Claude Code, the first thing I went looking for was a dashboard. 25052 was right there, well thought out, exactly the panels I wanted. But it's KQL on Application Insights, and our observability stack is Prometheus and Grafana. As far as I can tell, that's most teams.

The metrics themselves are fine. Claude Code speaks OTLP, and OTLP works with everyone.…