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/installnpx skills add johnkueh/bq-analytics --skill installgit 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 | $0.00085 | $0.08709 |
| Opus 5 | $0.00043 | $0.04355 |
| Sonnet 5 | $0.00017 | $0.01742 |
| Haiku 4.5 | $0.00009 | $0.00871 |
Grade A, and why
bq-analytics-install scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://<domain>/api/track \ How it starts
The opening of the file, as written. The whole thing — 682 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding bq-analytics to a project
This skill has three phases. Phases 1 and 2 are required; Phase 3 is optional but cheap.
- Phase 1: Provision + wire the SDK (steps 0–6 below)
- Phase 2: Instrument auth / payment / key events (the "Phase 2 — Instrumentation" section)
- Phase 3: Feature flags via Vercel Edge Config (the "Phase 3 — Feature flags" section). Skip unless asked, or if the project shows signs of needing flags (PostHog/LD/GrowthBook in deps, hand-rolled
if (FEATURE_*)gating). Day-to-day flag operations live inclaude-skills/flags/SKILL.md.
Step 0 — Detect the runtime
bq-analytics' first-class server target is Next.js App Router on Vercel — the route factory (createTrackRoute) is designed for that, and the setup script provisions Vercel-specific env vars. Other server frameworks work but require user-written adapters (the SDK ships generic Request → Response handlers; mapping into Hono / Express / Fastify is a few lines, see README).
Look at the repo to decide which path to follow.
| Signal | Stack | First-class? |
|---|---|---|
next.config.* + next in dependencies |
Next.js (likely on Vercel) | ✅ Yes — full install path |
express, fastify, koa in deps, no Next |
Node server (non-Next) | ⚠️ Partial — adapter required for the route handlers; pure server-side bqTransport works as-is |
hono in deps, no Next |
Hono (any runtime) | ⚠️ Partial — bq-analytics/hono middleware works; c.req.raw lets you call route factories directly |
expo / react-native + app.json |
Expo / RN (client SDK) | ✅ Yes — uses httpTransport to talk to a separate Next.js server |
no server framework, bin / tsx / ts-node scripts |
Node CLI | ✅ Yes — calls bqTransport directly, no route needed |
pyproject.toml, Gemfile, go.mod |
Non-Node | ⚠️ Manual — POST JSON to /api/track from any language |
HTML page with <script> only |
Browser-only | ✅ Yes via httpTransport to a Next.js server |
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.
- 3d ago First seen · 682 lines · 85 tokens per session scan A e65cb2a7cfc0
bq-analytics-install is a skill published in the GitHub repository johnkueh/bq-analytics (5 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 8,709 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…
eval-breakdown
Performs an exhaustive, question-by-question narrative diagnostic breakdown of an agent-eval benchmark run by analyzing questionanswerlog.md, evalsummary.json, and raw trajectory traces. Use when diagnosing low score causes, investigating the Memory Reuse vs. Traceability rubric clash, performing pre-release failure…
dbt-unit-tests
Generate dbt unit tests automatically for any model. Analyzes SQL logic (CASE/WHEN, JOINs, window functions, NULLs), creates type-correct mock inputs from manifest schema, and assembles complete YAML. Use when a user says "generate tests", "add unit tests", "test this model", or "test coverage" for dbt models.
cost-report
Analyze Snowflake query costs and identify optimization opportunities.
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…
pii-audit
Classify schema columns for PII (SSN, email, phone, name, address, credit card) and check whether queries expose them. Use for GDPR/CCPA/HIPAA compliance audits.