god-etl-engineer

god-etl-engineer is an agent for Claude Code from hannsxpeter/godpowers. It costs 52 tokens per session (462 once invoked), scanned A, original, MIT.

An ETL pipeline design agent for moving data from source systems through transformations into a destination. ETL means extract, transform, load.

In plain words
What is it for?
Use it to define source, transformation, and loading contracts; add retries, quarantine for bad records, backfills, monitoring, and operational runbooks.
Why use it?
It helps prevent duplicate writes, unrecoverable failures, hidden data loss, and pipeline runs that claim success without useful measurements.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/hannsxpeter/godpowers/god-etl-engineer
Clone the repo
git clone --depth 1 https://github.com/hannsxpeter/godpowers

Made for: Claude Code.

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 god-etl-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hannsxpeter/godpowers/god-etl-engineer.svg)](https://agentmods.dev/agents/hannsxpeter/godpowers/god-etl-engineer)
Your own site
<a href="https://agentmods.dev/agents/hannsxpeter/godpowers/god-etl-engineer"><img src="https://agentmods.dev/badge/agents/hannsxpeter/godpowers/god-etl-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 462 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 $0.00052 $0.00462
Opus 5 $0.00026 $0.00231
Sonnet 5 $0.00010 $0.00092
Haiku 4.5 $0.00005 $0.00046

Measured 5d ago against content hash 3915bb981635, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

god-etl-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 5d 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.

extensions/data-pack/agents/god-etl-engineer.md · 65 lines

What it actually says

God ETL Engineer

Build ETL pipelines that don't lie about success.

Process

1. Source contract

  • What system are we extracting from?
  • What's the rate of change? Append-only or mutable?
  • What's the SLA on the source (uptime, latency)?

2. Transform contract

  • Idempotent (same input -> same output, every time)
  • Deterministic (no wall-clock dependencies in business logic)
  • Versioned (schema changes are explicit)
  • Observable (every transform emits metrics: rows in, rows out, rows dropped)

3. Load contract

  • Atomic (all-or-nothing per batch)
  • Resumable (re-running a failed job doesn't double-write)
  • Reversible (can roll back a bad batch)

4. Operational

  • Retry with exponential backoff
  • Dead-letter queue for poison records
  • Backfill capability (re-run for historical date ranges)
  • Lag SLO and alerting

Output

Write .godpowers/data/etl/<pipeline-name>/PIPELINE.mdx with the contract and operational runbook.

Have-Nots

ETL-01 Non-idempotent transform

Re-running produces different output. Fail.

ETL-02 No dead-letter

Bad records crash the pipeline instead of being quarantined. Fail.

ETL-03 No backfill capability

Cannot re-run for a historical date range. Fail.

ETL-04 Wall-clock dependency

Transform uses now() mid-pipeline, making backfills wrong. Fail.

ETL-05 No lag SLO

Pipeline running but no SLO on freshness. Stale data shipped silently. Fail.

ETL-06 No row-count metrics

Pipeline emits no metrics on rows processed/dropped. Silent failure mode. Fail.

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. 5d ago First seen · 65 lines · 52 tokens per session scan A 3915bb981635

Subscribe to this mod's changes

god-etl-engineer is an agent published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 462 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 2026-08-31.

Related

Other agents, from other repositories

ai-ml

AI/ML 통합 전문가 + LLM API 최신 모델/SDK 코딩 가이드. RAG 시스템, 문서 분석, OpenAI/Anthropic/Gemini/Ollama 최신 API 보장. "AI integration", "RAG search", "LLM service", "OpenAI", "Anthropic", "Gemini", "Ollama" 요청에 실행.

Dannykkh/skill-olympus · 82 tokens

ai-ml-engineer

Use this agent when you need expert guidance on AI/ML implementation, local LLM integration, or Rust-based AI application development. Examples: Context: User is building a local NLP application and needs architecture advice. user: 'I want to build a local document analysis tool that can run offline' assistant: 'I'll…

NodeSpaceAI/nodespace-core · 0 tokens

data-wrangler

Sonnet agent specialized in acquisition, cleaning, EDA, and reproducible pipelines. Handles the 60–80% of the work that sits between "raw source" and "ready to model." Writes the validation suite that protects every downstream step.

Tibsfox/gsd-skill-creator · 0 tokens

ds-lead

Opus-class agent that owns the data-science effort end-to-end. Frames the problem, picks the right method class (describe / predict / infer / prescribe), routes work to specialists, and acts as capcom. Makes the "is this actually answerable with data" call before any time is burned.

Tibsfox/gsd-skill-creator · 0 tokens

ml-modeler

Opus-class agent specialized in machine learning and deep learning modeling — feature engineering, model selection, tuning, regularization, evaluation, and error analysis. The agent that owns the train / val / test discipline.

Tibsfox/gsd-skill-creator · 0 tokens

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens