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-product-thinkinggit 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-product-thinking)<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/data-product-thinking"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-product-thinking/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/data-product-thinking"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-product-thinking.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.00741 |
| Opus 5 | $0.00032 | $0.00370 |
| Sonnet 5 | $0.00013 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
data-product-thinking 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Principles
Apply these when making data product decisions:
-
Trust over features. A single data quality incident can destroy months of trust. One bad number in a board deck costs more than a delayed feature. Protect data accuracy before adding capabilities.
-
Outcomes over outputs. "47 dashboards and no answers" is the failure mode. Define what decisions the data product enables before defining what data it needs. Measure decisions enabled, revenue generated, time saved. Not models deployed or dashboards built.
-
Teams over tools. Technology is 20% of data product success. The other 80% is people, process, and product thinking. Don't lead with tool selection.
-
Uncertainty over certainty. Fix the time, vary the scope. Six-week cycles with variable scope beat two-week sprints with fixed scope for data products, where discovery is continuous.
-
Ownership over handoffs. Every handoff loses context. The team that discovers the problem should own it through delivery.
Five-Risk Evaluation Model
Before committing to any data product bet, evaluate all five risks:
- Value risk - Will customers actually use this? (Validate with 3+ customer data points)
- Usability risk - Can they figure it out without training?
- Feasibility risk - Can we build it with available data and infrastructure?
- Business viability risk - Does it work for the business model?
- Ethical data risk - Can we build it without bias, privacy violations, or unintended harm? (This is the 5th risk unique to data products. See
ethical-risk-assessmentfor the full framework.)
CRITICAL: Never skip ethical data risk. A technically correct model that produces biased outcomes is worse than no model.
Decision Framing
ALWAYS start with the problem, not the data. "Payers need to reduce readmissions" before "we have claims data."
ALWAYS define success metrics before data requirements. Build an outcome metric tree:
- Business outcome (reduce readmissions 10%)
- Product outcome (clinical decisions 3x faster)
- Feature outcome (risk scores updated real-time)
- Leading indicator (query latency under 1 second)
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.
- 9d ago First seen · 61 lines · 65 tokens per session scan A 5491c949b9f5
data-product-thinking is a skill published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 741 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
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
add-ai-webapi
Integrates Power Pages generative-AI summarization APIs (PREVIEW) into a Single Page Application (SPA) site — the Search Summary API and the Data Summarization API — on any record-detail or list page. Generates per-target service code (CSRF-handled) and AI site settings; delegates Web API settings, table permissions…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
nano-banana
This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…
prompt-engineer
Use when the user asks to improve, optimize, rewrite, debug, or shorten a prompt, or asks why a prompt is producing bad output. Do NOT use for writing a Claude Code SKILL.md — that needs skill structure rules, not prompt techniques.
meta-prompting
Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…