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 j4flmao/agent-skills --skill data-cataloggit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/data-catalog)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/data-catalog"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/data-catalog/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/j4flmao/agent-skills/data-catalog"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/data-catalog.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 | $0.00102 | $0.05501 |
| Opus 5 | $0.00051 | $0.02750 |
| Sonnet 5 | $0.00020 | $0.01100 |
| Haiku 4.5 | $0.00010 | $0.00550 |
Grade B, and why
data-data-catalog scanned grade B with 2 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 7d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post( "http://datahub-gms:8080/api/graphql", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.post( How it starts
The opening of the file, as written. The whole thing — 607 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Data Catalog
Purpose
Design and deploy a data catalog platform with metadata ingestion, column-level lineage, business glossary, data discovery, ownership model, and usage analytics.
Agent Protocol
Trigger
Exact user phrases: "data catalog", "DataHub", "Amundsen", "Apache Atlas", "OpenMetadata", "metadata management", "data discovery", "business glossary", "data lineage", "data ownership", "column-level lineage", "metadata ingestion".
Input Context
- Existing data stack (warehouse, lake, BI tools)
- Data catalog tool in consideration (if any)
- Data governance maturity level
- Number of data assets and teams
- Compliance requirements (GDPR, SOX, HIPAA)
- Current metadata sources (alerts, logs, metastore)
Output Artifact
Data catalog architecture with platform selection, metadata ingestion pipeline design, governance model with glossary and ownership, and usage analytics framework.
Response Format
# Catalog platform selection matrix
# Metadata ingestion pipeline
# Business glossary structure
# Ownership & stewardship model
# Usage analytics schema
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Catalog platform selected with rationale
- Metadata ingestion pipelines configured for all sources
- Column-level lineage established for critical datasets
- Business glossary defined with domains and terms
- Data ownership assigned with stewardship workflow
- Search and discovery configured with facets
- Usage analytics tracking enabled
Max Response Length
350 lines of configuration.
Workflow
Step 1: Select Catalog Platform
| Platform | Strengths | Weaknesses | Best For |
|---|---|---|---|
| DataHub | Column-level lineage, real-time push, GraphQL API | Complex deployment | ML-first orgs, real-time metadata |
| Amundsen | Simple search, good Tableau integration | Limited lineage, Python-only | Search-first use cases |
| OpenMetadata | Ingestion framework, role-based access, UI | Newer ecosystem, smaller community | Organizations wanting all-in-one |
| Apache Atlas | Hadoop-native, tag-based policies | Outdated UX, heavy | Existing Hadoop ecosystem |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/catalog-api-examples.md 3.4 KB
- references/catalog-data-discovery.md 971 B
- references/catalog-governance.md 935 B
- references/catalog-metadata-automation.md 5.1 KB
- references/catalog-platforms.md 3.0 KB
- references/catalog-search-discovery.md 4.4 KB
- references/data-catalog-metadata-management.md 17 KB
- references/data-catalog-search-discovery.md 14 KB
- references/metadata-ingestion-patterns.md 4.7 KB
- references/metadata-management.md 3.5 KB
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.
- 7d ago First seen · 607 lines · 102 tokens per session scan B 46ea8a13d5e6
data-data-catalog is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 5,501 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
portaljs-add-resource
Add another file (resource) to an EXISTING dataset in a PortalJS portal — a data dictionary, methodology, or an additional data file. Turns a single-file dataset into a multi-resource one; the showcase renders a section per resource. Use when a dataset needs a second file, such as a data dictionary, methodology doc…
metaxy
This skill should be used when the user asks to "define a feature", "create a BaseFeature class", "track feature versions", "set up metadata store", "field-level lineage", "FieldSpec", "FeatureDep", "run metaxy CLI", "metaxy migrations", "metaxy lock", "lock features", "external features", "multi-environment"…
mediabrain-reader
Analysiert bereitgestellte Medienlisten und Metadaten unabhängig von einer bestimmten Medien-App.
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
playwright-validation
Use when validating UI changes in a branch require Playwright E2E testing. Reviews branch changes, validates UI with Playwright MCP, and adds missing test cases.