Built In Metrics
launchdarkly/agent-skillsYou can add LaunchDarkly metrics to any AI agent call. This skill helps you pick the easiest way to track duration, tokens, and success or error. It walks you through a four-tier ladder. You start at the top and stop at the first tier that fits your code. The goal is to use the least amount of extra work while still getting all the data the monitoring tab needs.
Developers who use an AI SDK like OpenAI, LangChain, or a custom provider will find this useful. The skill tells you exactly what pattern to follow. For example, if your call is a chat loop you can use the managed runner. If not, you might use a provider package or a custom extractor. Only as a last resort do you write manual tracker calls.
Add Built In Metrics skill to your workflow
Global
mkdir -p ~/.claude/skills/built-in-metricsProject
mkdir -p .claude/skills/built-in-metricsSource Repository
More Monitoring & Observability Claude Code Skills
Appinsights Instrumentationmicrosoft/azure-skills
Learn how to add Azure Application Insights monitoring to your web app
Azure Kustomicrosoft/azure-skills
Run fast KQL queries on Azure Data Explorer for log and telemetry analysis
Caveman Statsjuliusbrussee/caveman
See real token usage and estimated savings directly from your session log
Azure Observabilitymicrosoft/azure-skills
Track Azure app errors, performance, and infrastructure with monitoring tools
Convex Performance Auditget-convex/agent-skills
Find and fix Convex performance problems with step-by-step diagnostic guidance
Google Agents Cli Observabilitygoogle/agents-cli
Set up tracing, logging, and analytics for your ADK agents easily
Golang Observabilitysamber/cc-skills-golang
Monitor your Go services with logs metrics traces and profiling
Golang Samber Slogsamber/cc-skills-golang
Compose, sample, and route Go logs to multiple backends with ease