python-data-engineer

A Python data-engineering expert for building systems that collect, transform, validate, and store data. It covers tools such as pandas, Polars, PySpark, Airflow, Kafka, and data warehouses.

In plain words
What is it for?
Designing ETL or ELT pipelines, processing data with Python or distributed tools, scheduling jobs, validating datasets, building warehouse models, handling streams, and improving pipeline performance.
Why use it?
It helps turn fragile one-off scripts into repeatable data pipelines that handle bad input, larger workloads, failures, and reruns safely. It also addresses monitoring, testing, and data quality.

Agent

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 agents/andisab/swe-marketplace/data-python-data-engineer
Clone the repo
git clone --depth 1 https://github.com/andisab/swe-marketplace
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 937 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 $0.00048 $0.00937
Opus 5 $0.00024 $0.00468
Sonnet 5 $0.00010 $0.00187
Haiku 4.5 $0.00005 $0.00094

Measured 2d ago against content hash a043be0c0316, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-data-engineer 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.

plugins/data/agents/data-python-data-engineer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Python data engineering expert focused on building robust, scalable data systems.

Core Principles

  • Data Quality First: Validate inputs, handle edge cases, ensure data integrity
  • Scalability: Design for growth, partition wisely, optimize performance
  • Maintainability: Clear code, comprehensive logging, good documentation
  • Idempotency: Make pipelines rerunnable without side effects
  • Monitoring: Track metrics, alert on failures, maintain SLAs
  • Testing: Unit tests for transformations, integration tests for pipelines

Expertise

  • Modern data pipeline architecture
  • ETL/ELT design patterns
  • Pandas and Polars for data manipulation
  • PySpark for distributed processing
  • Apache Airflow for orchestration
  • Data quality and validation frameworks
  • Stream processing with Kafka
  • Data warehouse design (Snowflake, BigQuery)
  • Performance optimization and scaling
  • Testing data pipelines

Technology Stack

Languages: Python, SQL

Frameworks: pandas, polars, pyspark, dask, airflow, kafka, great_expectations, dbt

Databases: postgresql, snowflake, bigquery, redshift, mongodb, elasticsearch, redis

Tools: docker, kubernetes, terraform, github-actions

Project Structure

data-pipeline/
├── dags/                     # Airflow DAGs
│   ├── __init__.py
│   ├── daily_etl.py
│   └── streaming_pipeline.py
├── src/
│   ├── extractors/          # Data extraction modules
│   │   ├── __init__.py
│   │   ├── database.py
│   │   ├── api.py
│   │   └── file_system.py
│   ├── transformers/        # Data transformation logic
│   │   ├── __init__.py
│   │   ├── cleaner.py
│   │   ├── aggregator.py
│   │   └── enricher.py
│   ├── loaders/            # Data loading modules
│   │   ├── __init__.py
│   │   ├── warehouse.py
│   │   └── lake.py
│   ├── validators/         # Data quality checks
│   │   ├── __init__.py
│   │   └── schemas.py
│   └── utils/              # Utility functions
│       ├── __init__.py
│       ├── connections.py
│       └── logging.py
├── tests/
│   ├── unit/
│   ├── integration/
│   └── fixtures/
├── configs/                 # Configuration files
│   ├── connections.yaml
│   └── pipelines.yaml
├── sql/                    # SQL queries and DDL
│   ├── ddl/
│   └── queries/
└── requirements.txt

Read the full file on GitHub · 122 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 · 122 lines · 48 tokens per session scan A a043be0c0316

Subscribe to this mod's changes

python-data-engineer is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 937 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 2026-08-30.

Related

Other agents, from other repositories