Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PostHog/posthog-foss --skill querying-production-databases-via-metabasegit clone --depth 1 https://github.com/PostHog/posthog-fossWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/posthog/posthog-foss/querying-production-databases-via-metabase)<a href="https://agentmods.dev/skills/posthog/posthog-foss/querying-production-databases-via-metabase"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/querying-production-databases-via-metabase/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/posthog/posthog-foss/querying-production-databases-via-metabase"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/querying-production-databases-via-metabase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.02717 |
| Opus 5 | $0.00039 | $0.01358 |
| Sonnet 5 | $0.00015 | $0.00543 |
| Haiku 4.5 | $0.00008 | $0.00272 |
Grade A, and why
querying-production-databases-via-metabase scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`metabase:cookie` exists for humans who want to hand-roll `curl` against This is a copy
88% identical to query-clickhouse-via-metabase — 97 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Querying production databases via Metabase
PostHog's production databases are reachable for ad-hoc, read-only analysis through internal Metabase instances. Both Metabases sit behind an AWS ALB with Cognito OAuth, so authentication is SSO-gated — Metabase API keys alone won't work.
Two engines are behind the same API surface, and the reason to reach for each is different:
- ClickHouse —
system.query_loganalysis: which queries are slow, what they read, who runs them. - Postgres (the app database) — the real query plan for an app query, and how a per-project table's rows spread across the fleet.
For pre-built canned ClickHouse queries (slow query summaries, materialization
analysis), see the query-performance-analysis repo, which is the source of
truth for those and uses the same Metabase API surface.
Environment
| Region | Metabase URL |
|---|---|
| US | https://metabase.prod-us.posthog.dev |
| EU | https://metabase.prod-eu.posthog.dev |
Database IDs are not stable — they change when Metabase's metadata DB is rebuilt or connections are re-added. Never hardcode an ID. Always discover the current list:
hogli metabase:databases --region us
hogli metabase:databases --region eu
Regional layout (names may vary; re-check with metabase:databases):
- US exposes one ClickHouse database (used for
query_logand data reads). - EU exposes two ClickHouse databases — a query tier (use for
query_loganalysis) and a data tier (production reads: events, persons, etc.). Pick the one whose name indicates the query tier. - Both Metabases also expose Postgres databases (the app DB) and, on EU, the ingestion-layer and migrations databases.
Authentication
Use hogli to get a valid cookie. It opens the system browser for SSO,
captures cookies from the user's logged-in browser profile, and caches them
at ~/.config/posthog/metabase/cookie-{region} (mode 0600).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 283 lines · 77 tokens per session scan A 47998b72b26d
querying-production-databases-via-metabase is a skill published in the GitHub repository PostHog/posthog-foss (715 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,717 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 88% identical to query-clickhouse-via-metabase, differing in 97 lines, and is treated as a copy.
Other skills, from other repositories
alloydb-basics
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
db-repair
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a GBRAINDBACCESS marker (or an operator reports the brain database is down), run the hardcoded gbrain db-repair ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command …
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.