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 xSAVIKx/okf-skills --skill okf-bigquerygit clone --depth 1 https://github.com/xSAVIKx/okf-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/xsavikx/okf-skills/okf-bigquery)<a href="https://agentmods.dev/skills/xsavikx/okf-skills/okf-bigquery"><img src="https://agentmods.dev/badge/skills/xsavikx/okf-skills/okf-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/xsavikx/okf-skills/okf-bigquery"><img src="https://agentmods.dev/badge/skills/xsavikx/okf-skills/okf-bigquery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 39 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00900 |
| Opus 5 | $0.00032 | $0.00450 |
| Sonnet 5 | $0.00013 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
okf-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 12d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BigQuery OKF Connector
This skill provides a Go-based CLI tool to convert Google Cloud BigQuery dataset schemas and table/field descriptions into Open Knowledge Format (OKF) bundles, and synchronize comments/descriptions back to BigQuery tables and fields.
When to Use
Use this skill when you need to:
- Extract table structures, schemas, field descriptions, and dataset descriptions from a Google Cloud BigQuery dataset into a portable OKF bundle.
- Synchronize business descriptions or documentation changes written in an OKF bundle back into native BigQuery table and schema field descriptions.
Setup
The connector requires Go 1.24+ and utilizes the official Google Cloud BigQuery Client:
# Install the published binary (Go 1.24+) — no clone needed:
go install github.com/xSAVIKx/okf-skills/skills/[email protected]
# …or build from a clone of the repository:
cd skills/okf-bigquery
go build -o okf-bigquery .
How to Use
Ensure you have set your GCP credentials. Usually, this is done by setting the GOOGLE_APPLICATION_CREDENTIALS environment variable:
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/credentials.json"
1. Produce an OKF Bundle
Extract dataset schema metadata and descriptions:
./okf-bigquery produce --project <gcp-project-id> --dataset <dataset-id> --out <output-bundle-dir> [--tables <comma-separated-table-names>] [--sample <N>] [--profile] [--relationships] [--stats]
2. Ingest / Synchronize an OKF Bundle
Synchronize table and field descriptions from the OKF bundle back to BigQuery:
./okf-bigquery ingest --project <gcp-project-id> --dataset <dataset-id> --bundle <path-to-okf-bundle> [--sync]
Parameters:
--project(required): Google Cloud Project ID.--dataset(required): Target BigQuery dataset ID.--bundle(required for ingest): Path to the OKF bundle.--out(required for produce): Path to output OKF bundle.--tables(optional): Filter to extract only specific tables.--sample <N>(optional): Embed up to N sample rows per table as a## Samplesection in each table doc (default 0 = none).--profile(optional): Compute per-column statistics (non-null, null, distinct, min, max) and embed a## Data Profilesection.--relationships(optional): Extract informational foreign-key constraints into a## Relationshipssection.--stats(optional): Add a## Statssection with the table row count (from table metadata) and, when a timestamp-like column is detected, a freshness window (min/max). Constraints (## Constraints) and view definitions (## View Definition, views only) are emitted by default. BigQuery has no secondary indexes, so no Indexes section is produced.--sync(optional for ingest): If provided, calls the BigQuery API to update table and schema descriptions.
What ships with it
12 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.
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.
- 12d ago First seen · 74 lines · 63 tokens per session scan A cdcb73b14486
okf-bigquery is a skill published in the GitHub repository xSAVIKx/okf-skills (33 stars, last pushed 12d ago), licensed Apache-2.0. It adds 63 tokens to every session and 900 once invoked, about $0.0003 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
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
dbt-sf-to-bq-translator
Translates Snowflake dbt SQL models to Standardized BigQuery SQL. Handles SQL compilation, Jinja macro placeholder masking, BigQuery Translation Service migration workflows, AST-based config transformations, explicit type casting, JSON extraction standardization, and deduplication. Use when migrating Snowflake dbt…
bigquery-bigframes
Generates Python code using BigQuery DataFrames (BigFrames), the pandas/scikit-learn-style API over BigQuery. Use when writing BigFrames code or doing pandas-style dataframe/ML work against BigQuery (e.g. in a notebook). Don't use for SQL-first workflows or the google-cloud-bigquery client library — use…
google-cloud-solution-hybrid-search-alloydb
Discovers requirements and generates architectural, design, and deployment guidance for dynamic hybrid search systems by combining semantic search and keyword search. Optimized for AlloyDB hybrid search use cases in Google Cloud. Use when users need vector search combined with structured SQL filtering, faceted…
coverage-tracker
Run a Google Alerts-style keyword coverage tracker. Uses news-search for recent keyword queries, lets the LLM dedupe and classify real features versus junk, stores decisions in SQLite, and alerts only on new real coverage.
chroma-integration
Chroma local vector database setup and operations for development and production.