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/flagsnpx skills add johnkueh/bq-analytics --skill flagsgit 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 | $0.00094 | $0.02433 |
| Opus 5 | $0.00047 | $0.01216 |
| Sonnet 5 | $0.00019 | $0.00487 |
| Haiku 4.5 | $0.00009 | $0.00243 |
Grade A, and why
bq-analytics-flags 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bq-analytics feature flags
Flags live in a single Vercel Edge Config item under the key flags. The
SDK reads at runtime via edgeConfigSource(); you mutate via the
bq-flags CLI shipped in the package. Propagation is sub-second.
{
"new-checkout": { "on": true, "rollout": 0.5 },
"ai-suggestions": { "on": true, "users": ["u_john", "u_beta1"] },
"kill-old-flow": { "on": false }
}
Detect current state
Before doing anything, figure out which path you're on:
| Signal | What it means | Where to start |
|---|---|---|
bq-analytics in package.json deps and EDGE_CONFIG= in .env.local |
fully wired | jump to Operate |
bq-analytics in deps, no EDGE_CONFIG= |
events wired, flags not yet | Step 1 below |
| neither | greenfield | run /bq-analytics-install first; it handles flags as Phase 3 |
grep -E '"bq-analytics"' package.json && echo "sdk present"
grep -E '^EDGE_CONFIG=' .env.local 2>/dev/null && echo "edge config provisioned"
Step 1 — Add the flag dependency
pnpm add bq-analytics @vercel/edge-config
# or: npm i / yarn add
@vercel/edge-config is an optional peer of bq-analytics. Only needed
when using edgeConfigSource() server-side; browser/RN clients use
httpSource() and don't need it.
Step 2 — Provision Edge Config
./node_modules/bq-analytics/scripts/setup-edge-config.sh
What it does (idempotent — safe to re-run):
vercel linkif not already linked- Creates an Edge Config store named
bq-analytics-flags(or reuses one with that slug) - Initializes the
flagskey as{} - Mints a read token, pushes
EDGE_CONFIGenv var to Vercel Production vercel env pull .env.local --environment productionso local dev can read it
Note: only Production is set automatically (CLI quirk on preview/dev
envs). For full env propagation, set VERCEL_TOKEN first, or replicate
via the Vercel dashboard.
After this, bq-flags is available via pnpm exec bq-flags (or
./node_modules/.bin/bq-flags).
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 · 267 lines · 94 tokens per session scan A ba9f9bc68c89
bq-analytics-flags is a skill published in the GitHub repository johnkueh/bq-analytics (5 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 2,433 once invoked, about $0.0005 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…