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 sethdford/claude-skills --skill data-governancegit clone --depth 1 https://github.com/sethdford/claude-skillsWrote 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/sethdford/claude-skills/data-governance)<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.
<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>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 | $0.00037 | $0.00622 |
| Opus 5 | $0.00018 | $0.00311 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
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.
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
-
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.
-
Establish Metadata Catalog: Inventory all data assets: databases, tables, APIs, data lakes. For each: owner, description, lineage (source), refresh frequency, classification (public/confidential/PII).
-
Set Quality Standards: For critical datasets, define SLAs: freshness (how recent), completeness (% non-null), accuracy (validated against source), consistency (matches across systems).
-
Build Data Dictionary: Business definitions of key entities and attributes. Customer means "active subscriber". Amount means "invoice total in USD". Shared vocabulary reduces confusion.
-
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.
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.
- 11d ago First seen · 49 lines · 37 tokens per session scan A ce549764c561
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.
Other skills, from other repositories
cmd_gan_build
GAN pipeline: run gan-planner → gan-generator → gan-evaluator in sequence. Loops until evaluator score ≥ 7.0.
healthcare-phi-compliance
Protected Health Information (PHI) and Personally Identifiable Information (PII) compliance patterns for healthcare applications. Covers data classification, access control, audit trails, encryption, and common leak vectors.
cost-aware-llm-pipeline
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
regex-vs-llm-structured-text
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.