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-quality)<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/review-data-quality"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/review-data-quality/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/commands/hollandkevint/data-product-operator/review-data-quality"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/review-data-quality.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 | $0.00014 | $0.00999 |
| Opus 5 | $0.00007 | $0.00500 |
| Sonnet 5 | $0.00003 | $0.00200 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
review-data-quality 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Data Quality
Assess the quality of a data source, table, or pipeline across 5 dimensions. Produces a scored quality review with specific improvement recommendations.
Gather Context
If $ARGUMENTS provides a data source or table name, use it. Otherwise, ask:
Question 1: What data are you assessing? (table name, pipeline name, or data source)
Question 2: What is this data used for? (analytics dashboard, ML model input, API response, reporting)
Question 3: Do you have access to the data now, or should I work from documentation/schema only?
If the user provides a file path or schema, read it. If they describe the data verbally, work from that description.
Assess Each Dimension
Score each dimension 1-5 based on evidence. Ask clarifying questions if you can't assess a dimension.
Scoring Rubric
For each dimension, evaluate and assign a score:
Completeness (are expected records and fields present?)
- 5: <1% nulls in required fields, all expected records present
- 4: 1-5% nulls, minor gaps in expected records
- 3: 5-10% nulls, some expected records missing
- 2: 10-20% nulls, significant gaps
- 1: >20% missing data or entire expected segments absent
Accuracy (does the data reflect reality?)
- 5: <0.1% error rate, validated against gold standard
- 4: <1% error rate, spot-checked against known values
- 3: Occasional known errors, no systematic validation
- 2: Known systematic errors, manual reconciliation required
- 1: Nobody trusts the numbers
Timeliness (is the data fresh enough?)
- 5: Real-time or well within SLA
- 4: Mostly within SLA, occasional delays
- 3: Frequently approaching SLA limits
- 2: Regularly exceeds SLA, consumers compensate with workarounds
- 1: Data is days or weeks stale
Consistency (does the same fact look the same everywhere?)
- 5: Single source of truth, no conflicting definitions
- 4: Minor inconsistencies between systems, documented and managed
- 3: Multiple definitions exist, team knows which is "right"
- 2: Conflicting definitions cause confusion, manual reconciliation needed
- 1: "Revenue" means 3 different things to 3 different teams
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 · 126 lines · 14 tokens per session scan A 74a24342acd2
review-data-quality is a command published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 999 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
quick-prd
Generate a complete PRD with competitive analysis in one workflow.
ompm
A general entry point that interprets a request and sends it to the most suitable product-management guide or workflow. Product management covers deciding what to build, why to build it, and how to deliver it.
full-pm-cycle
A command that coordinates product management from researching a market and users through planning, design, delivery, and measuring results.
feature-launch
A command that coordinates a feature from its product requirements document through release and analysis after launch. A product requirements document describes what a feature should do and why.
ceo-review
Run a CEO-level strategic review of a feature before development.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.