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/jpantsjoha/googlecloud-plugin/bigquerynpx skills add jpantsjoha/googlecloud-plugin --skill bigquerygit clone --depth 1 https://github.com/jpantsjoha/googlecloud-pluginWhat 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 | $0.00089 | $0.00683 |
| Opus 5 | $0.00044 | $0.00342 |
| Sonnet 5 | $0.00018 | $0.00137 |
| Haiku 4.5 | $0.00009 | $0.00068 |
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 yesterday.
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.
What it actually says
BigQuery
Serverless, highly scalable data warehouse. Bills per bytes processed — always dry-run before executing queries on large datasets.
Safety Rule — Dry-Run First
# Estimate bytes before executing — always do this on unknown datasets
bq query --dry_run --use_legacy_sql=false 'SELECT * FROM dataset.table'
# Output: "Query successfully validated. Assuming the tables are not modified,
# running this query will process X bytes."
Core Patterns
Create a dataset
bq mk --dataset \
--location=REGION \
--description="Description" \
PROJECT_ID:DATASET_NAME
Run a query (with cost confirmation)
# 1. Dry-run first (see above)
# 2. Execute only after confirming cost
bq query --use_legacy_sql=false --location=REGION \
'SELECT field FROM `project.dataset.table` LIMIT 100'
Grant dataset access (least-privilege)
bq show --format=prettyjson PROJECT_ID:DATASET > /tmp/ds.json
# Edit roles in /tmp/ds.json, then:
bq update --source /tmp/ds.json PROJECT_ID:DATASET
Create partitioned table (cost control)
CREATE TABLE dataset.table (
event_date DATE,
user_id STRING
)
PARTITION BY event_date
OPTIONS (partition_expiration_days = 365);
Cost Controls
- Partition tables by date — queries on a partition scan only that partition
- Cluster tables by high-cardinality filter columns
- Set per-project quotas: IAM → Quotas → BigQuery — Query usage per day
- Use
LIMITin development; avoidSELECT *on multi-TB tables
References
What ships with it
1 file 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.
- yesterday First seen · 77 lines · 89 tokens per session scan A 721155aac1a9
bigquery is a skill published in the GitHub repository jpantsjoha/googlecloud-plugin (4 stars, last pushed 25d ago), licensed MIT. It adds 89 tokens to every session and 683 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
avoid-ai-writing
Audit and rewrite prose so it stops reading as machine-generated. Use this skill when asked to remove AI-isms, clean up AI writing, edit a draft for AI tells, audit a README, changelog, release note, PR description, or blog post for machine-sounding prose, or make text sound less like AI. Supports a detect-only mode…
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.