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.
git clone --depth 1 https://github.com/hollandkevint/data-product-operatorWrote 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/commands/hollandkevint/data-product-operator/review-data-model)<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/review-data-model"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/review-data-model.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00017 | $0.00775 |
| Opus 5 | $0.00009 | $0.00387 |
| Sonnet 5 | $0.00003 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
review-data-model 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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a Data Model
Evaluate a schema design for a data product. This review covers normalization strategy, naming conventions, relationship design, grain correctness, and extensibility. Output is conversational critique with specific recommendations.
Gather Context
If $ARGUMENTS provides a file path, read it. If it provides DDL or a description, use it directly. Otherwise, ask:
Question 1: Share your schema. Options: paste DDL, provide a file path, describe the tables and relationships.
Question 2: What is this data product used for? (analytics, reporting, ML features, API serving, operational data store)
Question 3: What query patterns matter most? (what questions will consumers ask this data?)
Review Checklist
Evaluate each area and provide specific feedback:
1. Grain Check
- Is the grain of each fact table clearly defined?
- Is there unexpected row multiplication from joins?
- Does the grain match the intended query patterns?
Flag: "This table has one row per [X]. Is that correct? Your query pattern suggests you need one row per [Y] instead."
2. Normalization Strategy
- Is the normalization level appropriate for the use case? (OLTP needs 3NF; analytics needs star schema)
- Are there unnecessary joins that could be eliminated with strategic denormalization?
- Are there One Big Table anti-patterns (full denormalization causing row explosion)?
Flag: "This many-to-many relationship between patients and diagnoses will cause [N]x row multiplication if fully denormalized. Use a bridge table instead."
3. Naming Conventions
- Are table and column names consistent? (snake_case, no abbreviations unless standard)
- Do fact tables use
fact_prefix and dimension tables usedim_prefix? - Do column names include units when ambiguous? (
duration_daysnotduration) - Are foreign keys named consistently? (
<dimension>_id)
Flag specific violations. Don't say "naming could be improved." Say "ptnt_id should be patient_id. los should be length_of_stay_days."
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.
- 8d ago First seen · 78 lines · 17 tokens per session scan A 063146b89b18
review-data-model is a command published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 775 once invoked, about $0.0001 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 commands, from other repositories
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
symfony-migrations
Create and manage Doctrine migrations for database schema changes.
v-memory-refresh
(Re)index docs/superpowers prose into the local V-memory cache so recall is current. Incremental by file hash; runs fully offline (FTS5, pure stdlib). Optionally enable the semantic lane with a one-time bootstrap. Run it after pulling new docs, or when /v:remember looks stale.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
data-flow-analysis
Trace how data flows through the system from input to output.
archetype-impact
Scan the current workspace for all references to a given archetype across templates (.oet / .t.json source, .opt compiled) and AQL files, producing an impact table useful before editing a widely-reused archetype.