Works with the AI Agents you already use
BigQuery FinOps Query & Storage Cost Auditor
Cut BigQuery scan and storage waste using read-only INFORMATION_SCHEMA metadata—with ranked dollar attribution and ready-to-review partitioning SQL.
$49
BigQuery FinOps Query & Storage Cost Auditor
Example session with this skill installed
Analyze our 30-day JOBS_BY_PROJECT and TABLE_STORAGE exports ($6.25/TiB) to rank top cost drivers, storage billing switches and SQL fixes.
- Read your context and instructions
- Compiled the bigquery finops query
$3,840/mo addressable waste identified across an uncached sa-looker SELECT * refresh storm ($750/mo), a 62% net PHYSICAL storage savings on analytics_prod (-$1,420/mo after time-travel), a time-travel churn trap warning on stg_churn, and dry-run-ready RECOMMENDED_PATCHES.sql.
Connects securely to your tools. The creator never sees your data.
About this skill
One unpartitioned Looker refresh loop with CURRENT_TIMESTAMP() or a dataset on the wrong logical/physical storage billing model quietly burns thousands of dollars a month while nobody wants to grant an audit tool read access to customer rows.
What your AI assistant does with it
- Zero-row metadataViewer audit: Generates and analyzes read-only INFORMATION_SCHEMA job and storage exports—never reading a single customer table row.
- 5 SQL anti-pattern detectors: Pinpoints SELECT * scans, unpartitioned joins, DATE(ts) filter bypasses, uncached BI refresh storms and unbounded MERGEs.
- Physical vs logical arbitrage: Models dataset storage savings under PHYSICAL billing—including 7-day time-travel and fail-safe bytes so high-churn datasets aren't trapped.
- Copy-paste Standard SQL DDL: Drafts PARTITION BY, CLUSTER BY, require_partition_filter and ALTER SCHEMA SQL patches ranked by monthly dollar savings.
How a run works
- Run --emit-extraction-sql to generate least-privilege INFORMATION_SCHEMA queries
- Export JOBS_BY_PROJECT and TABLE_STORAGE metadata CSV or JSON
- Run bq_finops_auditor.py to rank costliest query hashes, principals and tables
- Review dry-run RECOMMENDED_PATCHES.sql with your data team before applying DDL
Built for: Heads of Data & Platform, Analytics engineering leads, GCP FinOps practitioners.
Included: Skill instructions with DDL & storage-model STOP AND VERIFY gates, bq_finops_auditor.py: TiB cost attributor, anti-pattern linter & DDL generator, EXTRACTION_QUERIES.sql, RECOMMENDED_PATCHES.sql, Excel XML & HTML report, BigQuery Editions, partitioning/clustering & physical-storage FinOps guide, BI refresh-storm & storage-arbitrage evaluation case.
Part of the B2B Operations & FinOps suite by Production AI Agents. Every calculation runs locally in standard-library Python (Decimal math, zero hidden network calls) and pauses at a human STOP AND VERIFY gate before any external write or sign-off.
Read-only offline analyzer and Standard SQL patch generator; never executes DDL or modifies production datasets directly. Always review generated calculations, drafts and SQL/API payloads before executing external actions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
Requires
Permissions
File Scopes
bq_finops_auditor.py inspects metadata exports offline, never reads customer table rows, redacts SQL literals, and never executes DDL.