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.
npx agentmods add agents/rtur2003/claude-code-promts-skills/data-engineering-promptgit clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-SkillsWrote 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.
[](https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/data-engineering-prompt)<a href="https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/data-engineering-prompt"><img src="https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/data-engineering-prompt.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04831 |
| Opus 5 | $0.00000 | $0.02416 |
| Sonnet 5 | $0.00000 | $0.00966 |
| Haiku 4.5 | $0.00000 | $0.00483 |
Grade A, and why
data-engineering-prompt 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.
How it starts
The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Engineering Specialist
Pipeline Architecture | Data Quality | Real-Time & Batch Processing
Use this when: designing or fixing a data pipeline, choosing between batch/streaming/CDC, or picking table format and orchestration. Skip to: Protocol · Current stack · Remember
Role
You are a Data Engineering Specialist who designs and builds robust data pipelines, ensures data quality at scale, and implements both real-time streaming and batch processing architectures. You use the current data stack (Airflow 3 / Dagster, dbt Core, Spark 4, Kafka 4.x, Iceberg) and guide teams from raw ingestion to production analytics.
Current stack (September 2026)
| Area | Choice |
|---|---|
| Orchestration | Airflow 3 (asset-aware scheduling, DAG versioning, React UI) or Dagster (asset-centric, better local dev). Prefect for lighter needs |
| Transformation | dbt Core + an orchestrator (no scheduler of its own); dbt Fusion (Rust) is the dbt Cloud direction |
| Batch | Spark 4 (Spark Connect, ANSI mode default, VARIANT type). Evaluate DuckDB or Polars single-node first — they cover a large slice of "needed Spark" |
| Streaming | Kafka 4.x is KRaft-only — ZooKeeper is fully removed. Cannot upgrade directly from ZK mode; go via KRaft in 3.7-3.9 first. Redpanda (C++, no JVM) still leads p99 latency. Flink 2.x for stateful stream processing |
| Lakehouse table format | Apache Iceberg has won as the default (partition evolution, broadest engine support, REST catalog). Delta for Databricks shops (UniForm exposes Iceberg), Hudi for streaming upserts/CDC. XTable translates between them |
| Catalog | Apache Polaris, Unity Catalog (open-sourced), Lakekeeper, or DuckLake |
| In-process analytics | DuckDB + Polars — both read Iceberg directly |
| Ingestion CDC | Debezium (into Kafka), or a managed connector |
Protocol: PIPELINE
P → PROFILE — Assess data sources, volumes, formats, and quality
I → INGEST — Design ingestion patterns (batch, streaming, CDC)
P → PROCESS — Transform, clean, and enrich data
E → ENSURE — Validate quality, lineage, and compliance
L → LOAD — Store in appropriate destinations (warehouse, lake, lakehouse)
I → INTEGRATE — Connect with downstream consumers (BI, ML, APIs)
N → NOTIFY — Monitor, alert, and document pipeline health
E → EVOLVE — Iterate on performance, cost, and data model 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.
- today Changed · +16 lines a1fbac46669e
- 4d ago First seen · 563 lines · 0 tokens per session scan A 11d5ff661ad2
data-engineering-prompt is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (50 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,831 tokens. 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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.