What is data-catalog?

A workflow for creating a durable data catalog in a defined Markdown format. A data catalog describes business entities, their sources and properties, and how they relate, while preserving uncertainty and privacy details.

Use it to inventory engagement data, document entities and relationships, prepare an ERD, and validate the catalog with the supplied script.

It gives teams a consistent record of available data and prevents guessed relationships from being presented as confirmed facts.

data-catalog — Skill by microsoft

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.

agentmods

npx agentmods add skills/microsoft/hve-core/data-catalog

Any agent

npx skills add microsoft/hve-core --skill data-catalog

Clone the repo

git clone --depth 1 https://github.com/microsoft/hve-core

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,217 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00054	$0.01217
Opus 5	$0.00027	$0.00609
Sonnet 5	$0.00011	$0.00243
Haiku 4.5	$0.00005	$0.00122

Measured 2d ago against content hash 6089072adc31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-catalog 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 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/validate_catalog.py, tests/fuzz_harness.py, tests/test_validate_catalog.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/data-science-engineering/data-catalog/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Catalog Workflow

Goal

Produce a customer-readable Markdown catalog whose YAML frontmatter is a valid DS_CATALOG_V1 machine contract. Preserve uncertainty explicitly so inferred or assumed relationships never appear confirmed.

Flow

Confirm the engagement name and the caller-approved durable output path.
Inventory entities at business grain. Record source access, tier, volume, profile pointer, classification, lineage, and open questions without copying column-level profile data.
Assign every relationship a stable rel-* identifier. Record endpoints, maximum cardinality, both endpoint minimums, one or more paired join-key fields, confidence, and evidence basis.
Reconcile coverage counts with the entity and relationship records.
Render the human-readable sections from the YAML facts, ending with the canonical Data Science and Engineering Coaching disclaimer footer. Narrative can explain facts but cannot redefine them.
Validate the artifact with scripts/validate_catalog.py before treating it as ready for review.

Inputs

Engagement context and a caller-approved output path
Data source inventory and access status
Business entity names, grain, and declared relationships
Existing per-dataset profile paths, when available
Privacy classifications or standards citations produced by the owning privacy workflow

Success criteria

The frontmatter declares exactly catalog_version: DS_CATALOG_V1 and validates against assets/ds-catalog-v1.schema.json.
Entity IDs and relationship IDs are unique and stable. Every endpoint and lineage reference resolves.
Every relationship declares cardinality as its maximum multiplicity plus from_minimum and to_minimum as zero or one.
Join keys use one string on both sides or paired arrays of equal length, and record field names only without primary-key, foreign-key, or uniqueness roles.
Relationship confidence is one of confirmed, inferred, or assumed, and every relationship records its basis.
Classification uses the privacy-standards citation-field names. The catalog does not invent standards identifiers.
Column statistics and feature metadata remain behind profile_ref rather than being copied into the catalog.
Every customer-facing catalog ends with the canonical Data Science and Engineering Coaching disclaimer footer.

Read the full file on GitHub · 80 lines

Files

What ships with it

17 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.

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.

2d ago First seen · 80 lines · 54 tokens per session scan A 6089072adc31

Subscribe to this mod's changes

data-catalog is a skill published in the GitHub repository microsoft/hve-core (1,411 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,217 once invoked, about $0.0003 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.

Databases

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens