data-engineering

data-engineering is a skill for Claude Code from MonumentalSystems/Atlas-Agent-Teams. It costs 24 tokens per session (1,116 once invoked), scanned A, original, MIT.

Reference material for data engineering: moving, transforming, storing, and checking data. It explains ETL and ELT workflows, batch jobs, streaming systems, and architectures such as Lambda and Kappa.

In plain words
What is it for?
Designing scheduled or real-time pipelines, comparing batch and streaming architectures, selecting storage and processing tools, and planning validation and monitoring.
Why use it?
It helps teams choose an approach based on timing, scale, reliability, and complexity. It also describes concerns such as event ordering, replaying data, and maintaining data quality.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the data-science plugin — 4 skills, 1 command, 5 agents shipped together

Good fit Designing scheduled or real-time pipelines, comparing batch and streaming architectures, selecting storage and processing tools, and planning validation and monitoring.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/monumentalsystems/atlas-agent-teams/data-engineering
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 MonumentalSystems/Atlas-Agent-Teams --skill data-engineering
Clone the repo
git clone --depth 1 https://github.com/MonumentalSystems/Atlas-Agent-Teams

Made for: Claude Code.

Or install data-science, the plugin that ships this one along with the rest of its 4 skills, 1 command, 5 agents.

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/monumentalsystems/atlas-agent-teams/data-engineering.svg)](https://agentmods.dev/skills/monumentalsystems/atlas-agent-teams/data-engineering)
Your own site
<a href="https://agentmods.dev/skills/monumentalsystems/atlas-agent-teams/data-engineering"><img src="https://agentmods.dev/badge/skills/monumentalsystems/atlas-agent-teams/data-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,116 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01116
Opus 5 $0.00012 $0.00558
Sonnet 5 $0.00005 $0.00223
Haiku 4.5 $0.00002 $0.00112

Measured 7d ago against content hash 2bffc9cde00f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

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.

teams/data-science/skills/data-engineering/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Engineering

Data Pipeline Patterns

Batch Processing

  • Scheduled Jobs: Run data processing at fixed intervals (hourly, daily, weekly)
  • Use Cases: Historical analysis, reporting, data warehousing
  • Tools: Apache Spark, Hadoop, Airflow, dbt
  • Design Considerations: Latency tolerance, resource efficiency, cost optimization

Streaming Processing

  • Real-time Ingestion: Process data as it arrives with low latency
  • Use Cases: Real-time analytics, monitoring, fraud detection
  • Tools: Apache Kafka, Apache Flink, Apache Storm, Apache Beam
  • Design Considerations: Event ordering, exactly-once semantics, backpressure

Lambda Architecture

  • Batch Layer: Store immutable master dataset, compute batch views
  • Speed Layer: Process real-time data for low-latency queries
  • Serving Layer: Merge batch and real-time views for queries
  • Use Cases: Systems requiring both batch and real-time capabilities
  • Challenges: Complexity of maintaining two code paths

Kappa Architecture

  • Unified Processing: Use a single stream processing framework
  • Replay Capability: Reprocess data from the event log
  • Use Cases: Simplified architecture when batch is just fast streaming
  • Benefits: Reduced complexity, single codebase

ETL/ELT Best Practices

ETL (Extract, Transform, Load)

  • Extract: Pull data from source systems with minimal impact
  • Transform: Clean, validate, and transform data in a staging area
  • Load: Load processed data into the target system
  • Best Practices:
    • Minimize source system impact
    • Handle incremental updates efficiently
    • Validate data before loading
    • Document transformation logic

ELT (Extract, Load, Transform)

  • Extract: Pull raw data from source systems
  • Load: Load raw data into the target system (usually data warehouse)
  • Transform: Transform data within the target system using SQL
  • Best Practices:
    • Leverage data warehouse compute power
    • Maintain raw data for audit trails
    • Use dbt for transformation orchestration
    • Version control transformation logic

Read the full file on GitHub · 118 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. 7d ago First seen · 118 lines · 24 tokens per session scan A 2bffc9cde00f

Subscribe to this mod's changes

data-engineering is a skill published in the GitHub repository MonumentalSystems/Atlas-Agent-Teams (21 stars, last pushed 26d ago), licensed MIT. It adds 24 tokens to every session and 1,116 once invoked, about $0.0001 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