newrelic-experimental/newrelic-preflight
AI coding observability for Kiro. Tracks tool calls, cost, anti-patterns, and efficiency metrics — and (optionally) ships them to New Relic.
Use when the user asks about AI coding session cost, token usage, efficiency score, anti-patterns (thrashing, re-reading, stuck loops), task completion, budget status, prompt cache health, git workflow efficiency, or wants to query New Relic Preflight's observability data for this coding session, past sessions, or their team. Also use for weekly/team summaries, personal coaching insights, and platform-comparison requests.
Set up New Relic Preflight observability for Kiro — verify the preflight/preflight-collector binaries are installed, wire up hook-based tool-call capture, and choose local vs. cloud mode. Use right after this power connects for the first time, or whenever the user asks to set up, configure, or troubleshoot Preflight.