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 agentmods add skills/justvinhhere/bigquery-expert/bigquery-featuresnpx skills add justvinhhere/bigquery-expert --skill bigquery-featuresgit 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-features)<a href="https://agentmods.dev/skills/justvinhhere/bigquery-expert/bigquery-features"><img src="https://agentmods.dev/badge/skills/justvinhhere/bigquery-expert/bigquery-features.svg" alt="Measured on agentmods" 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 | $0.00164 | $0.00714 |
| Opus 5 | $0.00082 | $0.00357 |
| Sonnet 5 | $0.00033 | $0.00143 |
| Haiku 4.5 | $0.00016 | $0.00071 |
Grade A, and why
bigquery-features 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BigQuery Features
You are an expert on BigQuery-specific features that go beyond standard SQL. When a user asks about any BigQuery feature, provide clear, practical guidance backed by working examples.
Feature Quick Reference
| Feature | Use Case | Key Syntax |
|---|---|---|
| STRUCT/ARRAY | Nested data, denormalization | STRUCT<>, ARRAY<>, UNNEST() |
| MERGE | Upserts, SCD Type 2 | MERGE...WHEN MATCHED...WHEN NOT MATCHED |
| Scripting | Multi-step workflows | DECLARE, SET, IF, LOOP, BEGIN...END |
| Scheduled queries | Recurring ETL | @run_time, @run_date params |
| Remote functions | External compute | CREATE FUNCTION...REMOTE WITH CONNECTION |
| JSON functions | Semi-structured data | JSON_EXTRACT, JSON_VALUE, JSON_QUERY |
| Approx aggregation | Fast cardinality | APPROX_COUNT_DISTINCT, HLL_COUNT |
| Geography | Spatial analysis | ST_GEOGPOINT, ST_DISTANCE, ST_WITHIN |
| BQML | In-database ML | CREATE MODEL, ML.PREDICT, ML.EVALUATE |
| Search/Vector | Full-text & similarity | SEARCH(), VECTOR_SEARCH() |
| BI Engine | Sub-second dashboards | Reservation-based, auto-accelerates |
Behavioral Rules
When Explaining a Feature
For every feature question, provide all four of these:
- What it is -- concise definition and where it fits in BigQuery's architecture.
- When to use it -- concrete use cases and when it is preferable over alternatives.
- Working example -- complete, runnable BigQuery SQL that demonstrates the feature.
- Common pitfalls -- gotchas, limits, performance traps, and cost implications.
General Guidelines
- Always use BigQuery-specific syntax (backtick-quoted projects,
STRUCT<>notation,SAFE.prefix where relevant). - When a feature has cost implications (BQML training, MERGE DML quotas, BI Engine reservations), cross-reference the
bigquery-optimizationskill for cost-aware patterns. - Prefer practical patterns over theoretical explanations. Show SQL that can be copy-pasted and run.
- When multiple approaches exist (e.g., JSON_EXTRACT vs native JSON type), explain trade-offs clearly.
What ships with it
8 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-struct-array-unnest.md 2.0 KB
- references/02-merge-dml.md 3.4 KB
- references/03-scripting.md 2.4 KB
- references/04-json-functions.md 2.3 KB
- references/05-approximate-aggregation.md 2.6 KB
- references/06-geography-functions.md 2.5 KB
- references/07-bqml.md 2.6 KB
- references/08-search-vector.md 3.4 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.
- 5d ago First seen · 54 lines · 164 tokens per session scan A 3e7102fda5c1
bigquery-features is a skill published in the GitHub repository justvinhhere/bigquery-expert (15 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 164 tokens to every session and 714 once invoked, about $0.0008 per session on Opus 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
data-parity
Validate that two tables or query results are identical — or diagnose exactly how they differ. Discover schema, identify keys, profile cheaply, then diff. Use for migration validation, ETL regression, and query refactor verification.
cost-report
Analyze Snowflake query costs and identify optimization opportunities.
dbt-test
Add schema tests, unit tests, and data quality checks to dbt models. Use when validating data integrity, adding test definitions to schema.yml, writing unit tests, or practicing test-driven development in dbt. Powered by altimate-dbt.
query-optimize
Analyze and optimize SQL queries for better performance.
schema-migration
Analyze DDL migrations for data loss risks — type narrowing, missing defaults, dropped constraints, breaking column changes. Use before applying schema changes to production.
dbt-pr-review
Cloudflare-style AI code review for dbt/SQL pull requests. Produces a signed APPROVE/COMMENT/REQUESTCHANGES verdict where every blocking finding is backed by a deterministic engine call — column-lineage blast radius, query equivalence, PII classification, and A–F grade. Use to review a dbt PR or the working-tree…