What is bauplan-data-semantics?

A tool for reading and drafting meaning for tables and columns in a Bauplan data lakehouse. A lakehouse stores large datasets in tables; this information is kept as versioned Iceberg table and column documentation.

Use it to inspect table and column documentation, or draft missing documentation for data schemas. Applying drafts requires a separate write-capable workflow.

A column can contain plausible but misleading values when its meaning, units, or status rules are unclear. The tool helps clarify that meaning before data is queried or pipeline code is written.

bauplan-data-semantics — Skill for Claude Code by BauplanLabs

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 BauplanLabs/bauplan-skills --skill bauplan-data-semantics

Clone the repo

git clone --depth 1 https://github.com/BauplanLabs/bauplan-skills

Made for: Claude Code.

Or install bauplan, the plugin that ships this one along with the rest of its 9 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bauplanlabs/bauplan-skills/bauplan-data-semantics/github.svg)](https://agentmods.dev/skills/bauplanlabs/bauplan-skills/bauplan-data-semantics)

Your own site

<a href="https://agentmods.dev/skills/bauplanlabs/bauplan-skills/bauplan-data-semantics"><img src="https://agentmods.dev/badge/skills/bauplanlabs/bauplan-skills/bauplan-data-semantics/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bauplanlabs/bauplan-skills/bauplan-data-semantics"><img src="https://agentmods.dev/badge/skills/bauplanlabs/bauplan-skills/bauplan-data-semantics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,065 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.

Model	Per session	Once invoked
Fable 5.1	$0.00119	$0.03065
Opus 5.5	$0.00048	$0.01226
Sonnet 5.5	$0.00024	$0.00613
Haiku 4.5	$0.00012	$0.00307

Measured 25d ago against content hash d022281b1e25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bauplan-data-semantics 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 25d 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.

plugins/bauplan/skills/bauplan-data-semantics/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Semantics

Bauplan can hold contextual meaning for data in table metadata: a table-level comment and a per-column doc, both stored in Iceberg, both versioned per data branch. The contextual meaning, stored as table and column documentation, provides support for the semantic layer. This skill reads table and column documentation and drafts what it should say when it is missing.

Documentation cannot be written through the CLI or SDK — it is authored in pipeline code and materialized by a run — so applying a draft always belongs to a write-capable skill.

When to Use This Skill

Before using a semantically loaded column — money, duration, distance, counts, status
When a query returned a plausible number you suspect is wrong
When a user asks what a table or column means
When bauplan-data-pipeline or bauplan-migrate-to-typed-sdk needs docstring and TableField(doc=) text for schemas it is about to declare

For data quality profiling use bauplan-explore-data; for whether a question is answerable at all, bauplan-data-assessment; for a failed run, bauplan-debug-and-fix-pipeline.

Updating documentation that already exists is not yet covered here.

CRITICAL RULES

Read-only. Never edit models.py, *.sql, or a schema class. Never run, merge, or create a branch. Draft text and hand it off.
Never invent meaning. Draft only what the producing code, the upstream catalog, or the user supports. A confident wrong doc is worse than none, because it gets trusted.
Label every claim as read from the catalog or inferred by you.
Mind the branch. Documentation is branch-scoped: a table documented on one branch may be bare on another. Prefer the active branch; pass --ref when reading a different branch, or comparing several at once.
Read docs as JSON whenever you act on what they say. The tty view truncates.

If any rule cannot be satisfied, STOP and report the blocker.

Reading the Semantic Layer

bauplan table get <namespace>.<table> -O json

Read the full file on GitHub · 274 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.

25d ago Changed d022281b1e25
1mo ago First seen · 274 lines · 119 tokens per session scan A dc5a575ed71b

Subscribe to this mod's changes

bauplan-data-semantics is a skill published in the GitHub repository BauplanLabs/bauplan-skills (17 stars, last pushed 3d ago), licensed MIT. It adds 119 tokens to every session and 3,065 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-19.

Data and AI Scientific

bauplan-data-semantics next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bauplan-data-semanticsBauplanLabs/bauplan-skills	Skill	17	3d ago	MIT	A	119	Claude Code
arboretoK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	55	Claude Code, Codex
deepspot-mK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	70	Claude Code
torchdrugK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	64	Claude Code
pyhealthK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	84	Claude Code, Codex
nemo-mbridge-perf-expert-parallel-overlapNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	56	Claude Code
ml-training-recipesOrchestra-Research/AI-Research-SKILLs	Skill	14k	27d ago	MIT	A	88	Claude Code