analytics-reviewlisted

# Analytics Review Pull live data from PostHog and the project's database, compare against saved baselines in memory, and surface actionable insights. ## Arguments - No arguments: full review (PostHog funnel + database usage + comparison) - `funnel`: PostHog funnel metrics only - `usage`: Database message/usage volume only - `users`: Per-user activity breakdown - `save`: Save current snapshot as a new baseline to memory ## Step 1/8: Find credentials Look for credentials in this order: ### PostHog 1. Check environment: `env | grep POSTHOG` 2. Check project `.envrc` files 3. Check memory files for PostHog project ID and API key 4. The PostHog API key starts with `phx_` (personal API key, not the project key `phc_`) **PostHog API base**: `https://us.i.posthog.com` (US) or `https://eu.i.posthog.com` (EU) ### Database 1. Check `server/.env` or `.env.local` for `DATABASE_DSN`, `DATABASE_URL`, `POSTGRES_URL`, or `SUPABASE_URL` 2. For Supabase projects, the DSN format is: `postgresql://postgres:<password>@db.<project-ref>.supabase.co:5432/postgres` 3. Use the project's Python environment (`uv run python3`) with `asyncpg` to query If credentials are missing, ask the user. ## Step 2/8: Read event architecture Check the project's PostHog events doc (usually `POSTHOG_EVENTS.md`) or memory for the event architecture. This tells you which events exist, what properties they carry, and what funnels they power. ## Step 3/8: Pull PostHog data Use the HogQL query endpoint (legacy i