Built In Metrics

This walks you through the four-tier ladder LaunchDarkly recommends for instrumenting AI provider calls with metrics tracking: managed runner, provider package with trackMetricsOf, custom extractor, or raw manual calls. The core insight is to default to the highest tier that fits your call shape, because going straight to manual tracker calls costs you drift and missed metrics. It audits your existing code to determine whether you have a chat loop, one-shot completion, or agent step, checks which provider package exists for your framework and language, then points you to reference implementations. Includes a migration path if you're still on the pre-0.20 SDK surface with aiclient.config instead of completion_config.

Install to Claude Code

npx -y skills add launchdarkly/agent-skills --skill built-in-metrics --agent claude-code