bq-generate

bq-generate is a command for Claude Code from justvinhhere/bigquery-expert. It costs 20 tokens per session (300 once invoked), scanned A, original, Apache-2.0.

A command that turns a plain-language description of the data you need into BigQuery SQL. BigQuery is Google Cloud’s service for analyzing large datasets with SQL.

In plain words
What is it for?
Use it to draft queries for reports, analysis, and data extraction when you provide the needed tables, columns, or business question.
Why use it?
It removes the need to write the query from scratch and makes its assumptions and possible improvements visible.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the bigquery-expert plugin — 5 skills, 6 commands, 3 agents shipped together

Install

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.

agentmods
npx agentmods add commands/justvinhhere/bigquery-expert/bq-generate
Clone the repo
git clone --depth 1 https://github.com/justvinhhere/bigquery-expert

Made for: Claude Code.

Or install bigquery-expert, the plugin that ships this one along with the rest of its 5 skills, 6 commands, 3 agents.

Wrote 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.

agentmods badge for bq-generate

README.md
[![agentmods](https://agentmods.dev/badge/commands/justvinhhere/bigquery-expert/bq-generate.svg)](https://agentmods.dev/commands/justvinhhere/bigquery-expert/bq-generate)
Your own site
<a href="https://agentmods.dev/commands/justvinhhere/bigquery-expert/bq-generate"><img src="https://agentmods.dev/badge/commands/justvinhhere/bigquery-expert/bq-generate.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 300 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00300
Opus 5 $0.00010 $0.00150
Sonnet 5 $0.00004 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 6d ago against content hash 003f8a7a7d99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bq-generate 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 6d 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.

commands/bq-generate.md · 37 lines

What it actually says

BigQuery Query Generation

Generate optimized BigQuery SQL using the bigquery-query-generation skill.

Instructions

  1. Determine what SQL to generate from the argument or current conversation context. If neither provides a clear description, ask the user what data they need.

  2. Gather schema context if available. Check whether the user has mentioned specific table names, column names, or project/dataset references. If not, use descriptive placeholders and state assumptions.

  3. Generate the SQL using the bigquery-query-generation skill. Proactively avoid all 11 anti-patterns from the bigquery-optimization skill while generating.

  4. Output using this format:

    ## Generated Query
    
    (fenced SQL code block)
    
    ## Assumptions
    - Schema, data type, and business logic assumptions.
    - Placeholder table/column names that need replacing.
    
    ## Anti-Patterns Proactively Avoided
    - List only the anti-patterns that were relevant to this query and actively avoided.
    
    ## Customization Notes
    - Suggestions for adapting the query: filters, additional columns, partitioning, etc.
    
  5. Prefer generating with stated assumptions over asking too many clarifying questions. Generate a working query first, then offer to refine.

Changes

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.

  1. 6d ago First seen · 37 lines · 20 tokens per session scan A 003f8a7a7d99

Subscribe to this mod's changes

bq-generate is a command published in the GitHub repository justvinhhere/bigquery-expert (15 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 300 once invoked, about $0.0001 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.