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 justvinhhere/bigquery-expert --skill bigquery-optimizationgit clone --depth 1 https://github.com/justvinhhere/bigquery-expertWrote 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/justvinhhere/bigquery-expert/bigquery-optimization)<a href="https://agentmods.dev/skills/justvinhhere/bigquery-expert/bigquery-optimization"><img src="https://agentmods.dev/badge/skills/justvinhhere/bigquery-expert/bigquery-optimization/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/justvinhhere/bigquery-expert/bigquery-optimization"><img src="https://agentmods.dev/badge/skills/justvinhhere/bigquery-expert/bigquery-optimization.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 | $0.00063 | $0.01018 |
| Opus 5.5 | $0.00025 | $0.00407 |
| Sonnet 5.5 | $0.00013 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
bigquery-optimization scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BigQuery SQL Optimization
You are a BigQuery SQL optimization expert. When you encounter BigQuery SQL, evaluate it against the 11 known anti-patterns documented in the references. When writing new SQL, proactively avoid all anti-patterns.
Anti-Pattern Quick Reference
| # | Name | What to Look For | Quick Fix | Severity |
|---|---|---|---|---|
| 1 | SimpleSelectStar | SELECT * on single-table query without JOINs or GROUP BY |
Specify only needed columns | High |
| 2 | SemiJoinWithoutAgg | IN/NOT IN subquery without DISTINCT or GROUP BY |
Add DISTINCT to subquery |
Medium |
| 3 | CTEsEvalMultipleTimes | CTE (WITH) alias referenced more than once | Convert to CREATE TEMP TABLE |
High |
| 4 | OrderByWithoutLimit | Outermost ORDER BY without LIMIT |
Add LIMIT clause |
Medium |
| 5 | StringComparison | REGEXP_CONTAINS with simple .*pattern.* |
Use LIKE '%pattern%' instead |
Low |
| 6 | LatestRecordWithAnalyticFun | ROW_NUMBER()/RANK() + WHERE rn = 1 |
Use ARRAY_AGG(... ORDER BY ... LIMIT 1) |
High |
| 7 | DynamicPredicate | Subquery inside WHERE predicate | Extract to DECLARE variable or CTE |
Medium |
| 8 | WhereOrder | AND predicates not ordered by selectivity | Reorder: = > >/< > >=/<= > != > LIKE (advisory -- BigQuery's optimizer may reorder independently) |
Low |
| 9 | JoinOrder | Smaller table on the left side of JOIN | Place largest table first (advisory -- optimizer usually handles this) | Low |
| 10 | MissingDropStatement | CREATE TEMP TABLE without corresponding DROP |
Add DROP TABLE at end of script |
Low |
| 11 | ConvertTableToTemp | CREATE TABLE + DROP TABLE in same script |
Use CREATE TEMP TABLE instead |
Low |
Behavioral Rules
When Writing New SQL
- Proactively apply all best practices. Never generate SQL that contains known anti-patterns.
- Select only the columns needed, not
SELECT *. - Use
LIKEinstead ofREGEXP_CONTAINSfor simple wildcard matches. - Place the largest table first in JOINs.
- Always add
LIMITwhen usingORDER BYunless ordering is required for correctness. - Use
ARRAY_AGGinstead ofROW_NUMBER()for "latest record per group" patterns.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/01-simple-select-star.md 930 B
- references/02-semi-join-without-agg.md 1.1 KB
- references/03-ctes-eval-multiple-times.md 1.3 KB
- references/04-order-by-without-limit.md 975 B
- references/05-string-comparison.md 979 B
- references/06-latest-record-with-analytic-fun.md 1.3 KB
- references/07-dynamic-predicate.md 1.6 KB
- references/08-where-order.md 1.7 KB
- references/09-join-order.md 1.6 KB
- references/10-missing-drop-statement.md 922 B
- references/11-convert-table-to-temp.md 1.2 KB
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.
- 1mo ago First seen · 81 lines · 63 tokens per session scan A 4bb82ae59e7d
bigquery-optimization is a skill published in the GitHub repository justvinhhere/bigquery-expert (17 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,018 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
usage
Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics…
dlt-connector
Connect SaaS data (HubSpot, Stripe, Salesforce, GitHub, Slack, etc.) to Wren Engine for SQL analysis. Guides the user through the full flow: install dlt, pick a SaaS source, set up credentials, run the data pipeline into DuckDB, then auto-generate a Wren semantic project from the loaded data. Use this skill whenever…
generate-mdl
Generate a Wren MDL project by exploring a database with available tools (SQLAlchemy, database drivers, MCP connectors, or raw SQL). Guides agents through schema discovery, type normalization, and MDL YAML generation using the wren CLI. Use when: user wants to create or set up a new MDL, onboard a new data source, or…
wren
Wren CLI for AI agents — a semantic SQL layer over 22+ databases (Postgres, MySQL, BigQuery, Snowflake, Spark, …). The actual workflow guides live inside the wren CLI itself; this is just a discovery stub. Use whenever the user asks a data question (how many, show me, top N, compare, trend, breakdown, metric, revenue…
transform
Use this to author and change a dbt project or a semantic layer: bootstrap a project (transform init), write or refactor models from staging to marts, add tests and docs, and define semantic models, entities, dimensions, and metrics in MetricFlow, Apache Ossie or SLayer YAML. Reach for it instead of editing model…
explore
Use this whenever you need to know what is actually in a database, warehouse, or DuckDB file before you trust it: inventory, column profiles, PII detection, grain and data-quality problems, verified joins, ER diagrams, ad-hoc SQL probes, segmentation, and the semantic layer a repo declares (dbt, Apache Ossie, or…