This is your audit layer for LaunchDarkly feature flags. It surfaces cleanup candidates by staleness, checks removal readiness with a safety verdict system (safe/caution/blocked), and helps you understand what's actually happening across environments. The workflow pushes you to categorize flags into actionable buckets rather than just listing them. The removal readiness tool is the standout piece here since it orchestrates multiple API calls to check for blockers like dependent flags or active requests. Good for quarterly cleanups or when you inherit a project and need to understand the flag landscape. It won't remove anything, just tells you what's worth investigating.
npx skills add https://github.com/launchdarkly/agent-skills --skill launchdarkly-flag-discovery