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/johnkueh/bq-analytics/querynpx skills add johnkueh/bq-analytics --skill querygit clone --depth 1 https://github.com/johnkueh/bq-analyticsWhat 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 | $0.00062 | $0.02505 |
| Opus 5 | $0.00031 | $0.01252 |
| Sonnet 5 | $0.00012 | $0.00501 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
bq-analytics-query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Querying bq-analytics
If bq isn't on PATH
The skill assumes the gcloud BigQuery CLI is callable as bq. On macOS with Homebrew (brew install gcloud-cli), the binaries land in /opt/homebrew/share/google-cloud-sdk/bin/ and are not symlinked into /opt/homebrew/bin/, so non-interactive shells (the ones tools like Claude Code spawn) won't find them — even when an interactive which bq works.
If a bq invocation fails with command not found, run one of:
# Option A — make it visible to non-interactive shells (loaded before .zshrc):
echo 'export PATH="/opt/homebrew/share/google-cloud-sdk/bin:$PATH"' >> ~/.zshenv
# Option B — symlink directly into a dir that's already on the system PATH:
ln -s /opt/homebrew/share/google-cloud-sdk/bin/{bq,gcloud,gsutil} /opt/homebrew/bin/
The PATH entry that lives in ~/.zshrc only helps interactive shells — ~/.zshenv is the right file for tooling. After either fix, plain bq query … calls below work as written.
Tables you can rely on
events.raw — append-only events. Hot columns: event_name, user_id, ts.
JSON: properties (use JSON_VALUE for filtering).
events.identifies — append-only user trait updates.
events.groups — append-only group trait updates.
events.user_groups — append-only user→group memberships.
events.users — view: latest traits per user_id.
events.groups_current — view: latest traits per (group_type, group_id).
events.user_groups_current — view: most-recent group per (user_id, group_type).
events.feedback — append-only product feedback. Hot columns: kind, user_id, ts.
kind ∈ {"bug", "request", "general", ...custom}.
JSON: properties. Plain TEXT: subject, message.
logs.raw — Server-side SDK log() calls (logger.* / analytics.log()).
Hot columns: ts, level, source, message.
JSON: fields. path/status/request_id are nullable
(set only when the caller supplies them).
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 · 244 lines · 62 tokens per session scan A bd0365354462
bq-analytics-query is a skill published in the GitHub repository johnkueh/bq-analytics (5 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 2,505 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 2026-08-31.
Other skills, from other repositories
agent-eval
Executes high-performance agent evaluations, multi-turn UserSim simulations, and declarative metric grading aligned with google/agents-cli and the Quality Flywheel. Publishes benchmark artifacts to the GCS Evaluation Registry, executes automated head-to-head delta comparisons (--compare-to), and optimizes system…
composio
Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help…
data-parity
Validate that two tables or query results are identical — or diagnose exactly how they differ. Discover schema, identify keys, profile cheaply, then diff. Use for migration validation, ETL regression, and query refactor verification.
dbt-analyze
Analyze downstream impact of dbt model changes using column-level lineage and the dependency graph. Use when evaluating the blast radius of a change before shipping. Powered by altimate-dbt.
dbt-docs
Document dbt models and columns in schema.yml with business context — model descriptions, column definitions, and doc blocks. Use when adding or improving documentation for discoverability. Powered by altimate-dbt.
dbt-pr-review
Cloudflare-style AI code review for dbt/SQL pull requests. Produces a signed APPROVE/COMMENT/REQUESTCHANGES verdict where every blocking finding is backed by a deterministic engine call — column-lineage blast radius, query equivalence, PII classification, and A–F grade. Use to review a dbt PR or the working-tree…