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 skills add hollandkevint/data-product-operator --skill data-model-designgit 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/skills/hollandkevint/data-product-operator/data-model-design)<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/data-model-design"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-model-design.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 | $0.00080 | $0.00827 |
| Opus 5 | $0.00040 | $0.00413 |
| Sonnet 5 | $0.00016 | $0.00165 |
| Haiku 4.5 | $0.00008 | $0.00083 |
Grade A, and why
data-model-design 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 7d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Star Schema as Default
For analytics data products, default to star schema with strategic denormalization:
Fact tables contain events at the lowest useful grain:
- One row per event (transaction, visit, measurement, interaction)
- Foreign keys to dimension tables
- Numeric measures (amount, count, duration)
- Timestamps at the grain of the analysis
Dimension tables contain context:
- Descriptive attributes for filtering and grouping
- Human-readable labels alongside codes
- Hierarchies for drill-down (region -> state -> city)
NEVER fully denormalize into One Big Table. Many-to-many relationships cause exponential row growth. A patient with 10 conditions and 5 medications creates 50 rows instead of 15.
ALWAYS start with the query patterns. What questions will consumers ask? Design the schema to make those queries simple. If 80% of queries filter by date and group by category, those should be the primary dimensions.
Slowly Changing Dimensions (SCD)
Type 1 - Overwrite the old value. Use when history doesn't matter (correcting a typo in a name).
Type 2 - Add a new row with effective dates. Use when you need to track what was true at a point in time (patient address at time of visit, product price at time of sale). Add effective_start_date, effective_end_date, and is_current flag.
Type 3 - Add a column for the previous value. Use when you only need one level of history (current_category, previous_category).
Default to Type 2 for any dimension where the business asks "what was it at the time of X?" Start with Type 1 for everything else and upgrade when the need emerges.
Architecture Decision Records
For every non-obvious modeling decision, write a lightweight ADR:
- Context: What situation prompted the decision?
- Options: What alternatives were considered?
- Decision: What was chosen and why?
- Consequences: What are the tradeoffs?
Keep ADRs in the repo alongside the schema. Future team members will ask "why is it modeled this way?" The ADR answers before they have to ask.
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.
- 7d ago First seen · 79 lines · 80 tokens per session scan A 2a502892fe21
data-model-design is a skill published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 827 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
add-sample-data
Use when the user wants to seed Dataverse tables with realistic sample records so a freshly-scaffolded code app shows real-looking data on first launch. Generates contextually appropriate rows from each table's schema and inserts them in dependency order. Mirrors…
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
ecto-patterns
Ecto patterns — schemas, changesets, queries, migrations, Multi, associations, preloads, upserts. Use when editing Repo calls, Ecto.Query, or schema fields. Skip for Ash.
ggsql
Write ggsql queries — a grammar of graphics for SQL. Use when the user wants to create, modify, or understand a ggsql visualization query.
bun-redis
Use when working with Redis in Bun (ioredis, Upstash), caching, pub/sub, session storage, or key-value operations.
bun-sqlite
Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.