data-engineering

data-engineering is a skill for Claude Code, Codex from hoangatg/ai-agent-toolkit. It costs 37 tokens per session (793 once invoked), scanned A, original, MIT.

A guide to designing data pipelines that move, transform, store, and prepare data for analysis. It covers ETL and ELT, batch and streaming processing, warehouses, and orchestration tools.

In plain words
What is it for?
Use it when building analytics infrastructure, choosing pipeline technologies, processing data in batches or in real time, designing warehouses, or structuring dbt models.
Why use it?
It helps organize reliable data flows instead of handling ingestion, transformations, storage, and scheduling as disconnected tasks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/hoangatg/ai-agent-toolkit/data-engineering
Any agent
npx skills add hoangatg/ai-agent-toolkit --skill data-engineering
Clone the repo
git clone --depth 1 https://github.com/hoangatg/ai-agent-toolkit

Made for: Claude Code, Codex.

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 data-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/data-engineering.svg)](https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/data-engineering)
Your own site
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/data-engineering"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/data-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 793 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00793
Opus 5 $0.00018 $0.00396
Sonnet 5 $0.00007 $0.00159
Haiku 4.5 $0.00004 $0.00079

Measured 2d ago against content hash 8ab659498108, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

data-engineering 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.

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.

.agent/skills/data-engineering/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Engineering

Move data reliably from where it is to where it needs to be.


1. Pipeline Architecture

ETL vs ELT

Approach Transform Where Best For
ETL Before loading Legacy DW, data cleansing
ELT After loading Modern cloud DW (BigQuery, Snowflake)

Pipeline Patterns

Pattern Use Case
Batch Daily/hourly aggregations
Streaming Real-time analytics, alerts
Micro-batch Near-real-time (Spark Streaming)
Lambda Batch + streaming combined
Kappa Streaming-only (simplicity)

2. Technology Selection

Layer Options
Ingestion Kafka, Debezium, Fivetran, Airbyte
Processing Spark, Flink, dbt, Pandas
Storage S3, GCS, Delta Lake, Iceberg
Warehouse BigQuery, Snowflake, Redshift, ClickHouse
Orchestration Airflow, Dagster, Prefect
Visualization Metabase, Looker, Superset

3. dbt Patterns

Concept Purpose
Sources Raw data documentation
Staging Clean, rename, type-cast
Intermediate Business logic transforms
Marts Final business-facing tables
Tests Data quality assertions

dbt Best Practices

Principle Application
DRY models Use CTEs and refs
Incremental Process only new data
Documentation Describe every model and column
Testing unique, not_null, relationships
Version control Git for all SQL transforms

4. Data Quality

Dimension Check
Completeness No missing required fields
Uniqueness No unexpected duplicates
Freshness Data is recent enough
Accuracy Values within expected ranges
Consistency Same data across systems

Tool Options

Tool Purpose
Great Expectations Python-based validation
dbt tests SQL-based assertions
Soda Data monitoring
Monte Carlo Data observability

Read the full file on GitHub · 116 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. 2d ago First seen · 116 lines · 37 tokens per session scan A 8ab659498108

Subscribe to this mod's changes

data-engineering is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 793 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 2026-09-03.