bauplan-safe-ingestion

bauplan-safe-ingestion is a skill for Claude Code from BauplanLabs/bauplan-skills. It costs 58 tokens per session (3,193 once invoked), scanned A, original, MIT.

A safe data-loading procedure for moving files such as Parquet, CSV, or JSONL from Amazon S3 into Bauplan, a data platform for versioned lakehouse tables. It uses a temporary branch and quality checks before publishing the data to the main branch.

In plain words
What is it for?
Use it to write Python-based S3 ingestion jobs with the Bauplan SDK, check the incoming data, and publish it only after validation succeeds.
Why use it?
It prevents unvalidated or broken data from reaching the shared main dataset. The isolated import and validation stages make it possible to inspect changes before merging them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the bauplan plugin — 7 skills shipped together

Good fit Use it to write Python-based S3 ingestion jobs with the Bauplan SDK, check the incoming data, and publish it only after validation succeeds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bauplanlabs/bauplan-skills/bauplan-safe-ingestion
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-safe-ingestion
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 7 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 bauplan-safe-ingestion

README.md
[![agentmods](https://agentmods.dev/badge/skills/bauplanlabs/bauplan-skills/bauplan-safe-ingestion/github.svg)](https://agentmods.dev/skills/bauplanlabs/bauplan-skills/bauplan-safe-ingestion)
Your own site
<a href="https://agentmods.dev/skills/bauplanlabs/bauplan-skills/bauplan-safe-ingestion"><img src="https://agentmods.dev/badge/skills/bauplanlabs/bauplan-skills/bauplan-safe-ingestion/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 bauplan-safe-ingestion

Your own site · 80×15
<a href="https://agentmods.dev/skills/bauplanlabs/bauplan-skills/bauplan-safe-ingestion"><img src="https://agentmods.dev/badge/skills/bauplanlabs/bauplan-skills/bauplan-safe-ingestion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,193 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00058 $0.03193
Opus 5 $0.00029 $0.01597
Sonnet 5 $0.00012 $0.00639
Haiku 4.5 $0.00006 $0.00319

Measured today against content hash bc08e07e6292, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bauplan-safe-ingestion 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 today.

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-safe-ingestion/SKILL.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Safe Ingestion

Safely ingest data from S3 into the Bauplan lakehouse by isolating changes on a temporary branch, running quality checks, and only merging to main after validation succeeds. This pattern is formally known as Write-Audit-Publish (WAP) in the Iceberg ecosystem.

Implement this as a Python script using the bauplan SDK. Do NOT use CLI commands for the ingestion itself.

Environment Setup

Before writing the script, check whether the project uses uv (look for pyproject.toml or uv.lock). If so, use uv run python to execute scripts and uv add to install packages. Otherwise, use the system python and pip install.

Ensure the required packages are installed:

  • bauplan (the Bauplan Python SDK — required)
  • polars (if validation logic needs DataFrame operations — zero-copy Arrow interop)

Do not use pandas. Bauplan's client.query() returns a PyArrow table directly — you can access columns with result.column("name")[0].as_py() or convert to Polars with pl.from_arrow(result). No .to_arrow() call is needed. Pandas requires a full data copy and is slower.

The three phases:

  1. Import — load data onto a temporary branch (never main)
  2. Validate — run quality checks before publishing
  3. Merge — promote to main only after validation passes

Branch safety: All operations happen on a temporary branch, NEVER on main. By default, branches are kept open for inspection after success or failure.

Atomic multi-table operations: merge_branch is atomic. You can create or modify multiple tables on a branch, and when you merge, either all changes apply to main or none do. This enables safe multi-table ingestion workflows.

Required User Input

Before writing the script, you MUST gather:

  1. S3 path (required): The S3 URI pattern for the source data (e.g., s3://bucket/path/*.parquet)
  2. Table name (required): The name for the target table
  3. Validation path (required): See "Choosing a Validation Path" below
  4. On success behavior (optional):
    • inspect (default): Keep the branch open for user inspection before merging
    • merge: Automatically merge to main and delete the branch
  5. On failure behavior (optional):
    • inspect (default): Leave the branch open for inspection/debugging
    • delete: Delete the failed branch

Read the full file on GitHub · 313 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. today Changed bc08e07e6292
  2. yesterday Changed · +3 lines 3b2b0a6e3e8d
  3. 11d ago First seen · 310 lines · 58 tokens per session scan A 9b8cb7ac393a

Subscribe to this mod's changes

bauplan-safe-ingestion is a skill published in the GitHub repository BauplanLabs/bauplan-skills (16 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 3,193 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.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens