data-governance

data-governance is a skill for Claude Code from sethdford/claude-skills. It costs 37 tokens per session (622 once invoked), scanned A, original, MIT.

A set of practices for deciding who owns organizational data, how its quality is measured, how it is described, and which privacy and compliance rules apply. It covers data origins, metadata, master records, access, and retention.

In plain words
What is it for?
Use it to define data owners, quality standards, metadata catalogues, lineage, retention rules, access controls, and policies for important customer or business data.
Why use it?
It reduces unclear responsibility, inconsistent data, missing documentation, and compliance risks when many teams manage shared information.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the data-architecture plugin — 8 skills shipped together

Good fit Use it to define data owners, quality standards, metadata catalogues, lineage, retention rules, access controls, and policies for important customer or business data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sethdford/claude-skills/data-governance
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.

Any agent
npx skills add sethdford/claude-skills --skill data-governance
Clone the repo
git clone --depth 1 https://github.com/sethdford/claude-skills

Made for: Claude Code.

Or install data-architecture, the plugin that ships this one along with the rest of its 8 skills.

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 data-governance

README.md
[![agentmods](https://agentmods.dev/badge/skills/sethdford/claude-skills/data-governance/github.svg)](https://agentmods.dev/skills/sethdford/claude-skills/data-governance)
Your own site
<a href="https://agentmods.dev/skills/sethdford/claude-skills/data-governance"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/data-governance/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 data-governance

Your own site · 80×15
<a href="https://agentmods.dev/skills/sethdford/claude-skills/data-governance"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/data-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 622 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 $0.00037 $0.00622
Opus 5 $0.00018 $0.00311
Sonnet 5 $0.00007 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 11d ago against content hash ce549764c561, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

data-governance 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 11d 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.

architect/data-architecture/skills/data-governance/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Governance

Establish organizational data management practices, ownership, quality standards, and compliance policies.

Context

You are building data governance practices. Define who owns data, how quality is enforced, compliance requirements, and metadata standards. Read organizational context, regulatory requirements, and existing data practices.

Domain Context

Based on enterprise data management practices:

  • Data Ownership: Clear accountability for data quality, availability, and compliance
  • Data Lineage: Track data origin, transformations, and dependencies
  • Data Quality: Accuracy, completeness, timeliness, consistency standards
  • Metadata Management: Catalog of data assets, definitions, classifications
  • Compliance: GDPR, CCPA, HIPAA, SOC2; data retention, access control
  • Master Data: Golden record of critical entities (customer, product); source of truth

Instructions

  1. Define Data Owner Roles: Who is accountable for each data domain? Product for customer data, Finance for transaction data. Owners define quality standards and usage policies.

  2. Establish Metadata Catalog: Inventory all data assets: databases, tables, APIs, data lakes. For each: owner, description, lineage (source), refresh frequency, classification (public/confidential/PII).

  3. Set Quality Standards: For critical datasets, define SLAs: freshness (how recent), completeness (% non-null), accuracy (validated against source), consistency (matches across systems).

  4. Build Data Dictionary: Business definitions of key entities and attributes. Customer means "active subscriber". Amount means "invoice total in USD". Shared vocabulary reduces confusion.

  5. Implement Access Control: Who can access what data? Implement principle of least privilege. GDPR: individuals can request deletion; log access to sensitive data.

Anti-Patterns

  • Governance Without Buy-In: Impose rules without business input. Result: ignored policies. Guard: Make data owners responsible for enforcement; governance enables business not obstructs.
  • Metadata Without Updates: Catalog created, then becomes stale. Result: inaccurate documentation. Guard: Automate metadata collection; make updates part of data pipeline changes.
  • No Enforcement Mechanism: Quality standards defined but not checked. Result: bad data in pipelines. Guard: Implement automated data quality checks; fail on breach.
  • Treating Governance as IT-Only: Business doesn't understand or support. Result: resistance, workarounds. Guard: Governance is business decision; IT implements and enforces.

Read the full file on GitHub · 49 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. 11d ago First seen · 49 lines · 37 tokens per session scan A ce549764c561

Subscribe to this mod's changes

data-governance is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 622 once invoked, about $0.0002 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 2026-08-30.