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 costory-io/costory-finops-mcp-skills --skill bigquerygit clone --depth 1 https://github.com/costory-io/costory-finops-mcp-skillsWrote 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/costory-io/costory-finops-mcp-skills/bigquery)<a href="https://agentmods.dev/skills/costory-io/costory-finops-mcp-skills/bigquery"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/bigquery/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/costory-io/costory-finops-mcp-skills/bigquery"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/bigquery.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 | $0.00115 | $0.03361 |
| Opus 5 | $0.00057 | $0.01681 |
| Sonnet 5 | $0.00023 | $0.00672 |
| Haiku 4.5 | $0.00012 | $0.00336 |
Grade A, and why
bigquery 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 2d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BigQuery
Invoice SKUs first. Bytes scanned, slot-ms, and table storage are not on the bill. Teach slots vs on-demand, open [BigQuery] BigQuery Dashboard, then allocate or optimize.
Not this if: GCP spend CUD leftover → recipes → gcp-spend-cud. Generic Explorer → query. Whole-bill "what changed" → recipes → explain-period-change.
Workflow
get_context— currency; notebq_*/user_emailif already ingestedsearch{ type: ["dashboards"], query: "BigQuery" }— use the template [BigQuery] BigQuery Dashboard. Org copies can differ. Never hardcode an id.getthat template for the URL. Do not walk widgets.- Teach Slots vs on-demand (two sentences): On-demand = pay per TiB scanned. Slots = pay for a pool; unused slots still cost, and bytes no longer price the job. Then the SKU table, then the caveat that matches the ask.
- Read the dashboard (order below). Branch: leftover Analysis → assignment / load jobs; storage →
TABLE_STORAGE; showback → Allocate; no labels → Jobs metadata. - Costory
queryonly after the dashboard. Persist viaquery/dashboards/virtual-dimensions. Nocreate_dashboardunless they ask to clone.
Slots vs on-demand
A slot is a unit of BigQuery compute. total_slot_ms in JOBS is how hard the query worked — it is not the invoice line unless you buy slots.
| On-demand | Slots (capacity / editions) | |
|---|---|---|
| What you buy | Nothing in advance | A reservation assigned to a project, folder, or org |
| Invoice meter | Bytes scanned (total_bytes_billed) |
Slot-hours reserved or autoscaled, used or not |
| Costory SKU | cos_sku contains Analysis (not Slots) |
cos_sku contains Edition (Standard / Enterprise / Enterprise Plus); service often BigQuery Reservation API |
| Narrow scan | Cheap | You still pay the reservation |
Wide SELECT * |
Expensive (TiB) | Same reservation price; the job occupies more slots / queues |
| LOAD / COPY / EXTRACT | Free | Uses the reservation if that job type is assigned |
| Idle | $0 | Baseline / committed slots still bill |
| Who used the $ | Each job’s bytes | Shared pool. Invoice does not split Edition SKUs per query unless Costory slot reallocation is on |
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.
- 2d ago First seen · 188 lines · 115 tokens per session scan A 0fcf4690895a
bigquery is a skill published in the GitHub repository costory-io/costory-finops-mcp-skills (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 115 tokens to every session and 3,361 once invoked, about $0.0006 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 2026-09-10.
Other skills, from other repositories
implementing-aws-macie-for-data-classification
Implement Amazon Macie to automatically discover, classify, and protect sensitive data in S3 buckets using machine learning and pattern matching for PII, financial data, and credentials detection.
aws-bedrock-data-automation-mcp
Analyze documents, images, videos, and audio.
hedis-measure-calculation
Provide deterministic Python and SQL for calculating Healthcare Effectiveness Data and Information Set (HEDIS) quality measures from claims and clinical data. Use when asked to 'calculate a HEDIS measure', 'check continuous enrollment', 'detect care gaps', 'compute utilization rates', 'identify high-cost claimants'…
databricks-platform-provisioning
Provision and test Databricks workspaces. Use when the user asks to create a workspace, set up a new environment, provision infrastructure, bootstrap Databricks, test a workspace, verify a deployment, or run validation checks against a Databricks workspace. Covers Azure, AWS, and GCP.
terraform-infrastructure-as-code
Comprehensive Terraform Infrastructure as Code skill covering resources, modules, state management, workspaces, providers, and advanced patterns for cloud-agnostic infrastructure deployment.
prowler-mcp
Creates MCP tools for Prowler MCP Server. Covers BaseTool pattern, model design, and API client usage. Trigger: When working in mcpserver/ on tools (BaseTool), models (MinimalSerializerMixin/fromapiresponse), or API client patterns.