review-data-quality

review-data-quality is a command for Claude Code from hollandkevint/data-product-operator. It costs 14 tokens per session (999 once invoked), scanned A, original, MIT.

A command that checks a data source, table, or pipeline across five data-quality areas and gives each area a score from 1 to 5. It also suggests improvements based on available evidence.

In plain words
What is it for?
Use it to assess data from a file, schema, documentation, or description, and produce scored findings and recommendations for improvement.
Why use it?
It gives teams a repeatable way to find missing, inaccurate, outdated, or inconsistent data before it affects dashboards, reports, APIs, or machine-learning models.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the data-product-operator plugin — 18 skills, 7 commands, 1 MCP server shipped together

Good fit Use it to assess data from a file, schema, documentation, or description, and produce scored findings and recommendations for improvement.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hollandkevint/data-product-operator/review-data-quality
Install

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.

Clone the repo
git clone --depth 1 https://github.com/hollandkevint/data-product-operator

Made for: Claude Code.

Or install data-product-operator, the plugin that ships this one along with the rest of its 18 skills, 7 commands, 1 MCP server.

Wrote 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.

agentmods badge for review-data-quality

README.md
[![agentmods](https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/review-data-quality/github.svg)](https://agentmods.dev/commands/hollandkevint/data-product-operator/review-data-quality)
Your own site
<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.

agentmods 80×15 button for review-data-quality

Your own site · 80×15
<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>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 999 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 74a24342acd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

commands/review-data-quality.md · 126 lines

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

Read the full file on GitHub · 126 lines

Changes

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.

  1. 9d ago First seen · 126 lines · 14 tokens per session scan A 74a24342acd2

Subscribe to this mod's changes

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.