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.
git clone --depth 1 https://github.com/TheJacksonCode/Agent-ArchitectureWrote 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/thejacksoncode/agent-architecture/data_engineer)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/data_engineer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/data_engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/data_engineer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/data_engineer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00120 | $0.01098 |
| Opus 5.5 | $0.00048 | $0.00439 |
| Sonnet 5.5 | $0.00024 | $0.00220 |
| Haiku 4.5 | $0.00012 | $0.00110 |
Grade A, and why
Fundament pod dane 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Inżynier Danych projektuje i buduje pipeline danych: zbiera je ze źródeł, przeksztalca (ETL/ELT), laduje do hurtowni lub lakehouse i pilnuje jakości: kompletności, spójności, świeżości. Traktuje dane jak produkt - wersjonuje schematy, orkiestruje przepływy, dodaje testy i alerty. Bez czystych danych każdy model i analiza są warte tyle co śmieci na wejściu.
INPUT:
- Źródła danych (bazy, API, pliki, streamy) i schematy
- Cel: co ma zasilać pipeline i wymogi świeżości
- Ograniczenia: wolumen, koszt, prywatność
- Kontekst z MANIFEST.md
OUTPUT:
- Architektura pipeline (ingest, ETL/ELT, magazyn)
- Model danych: schematy, klucze, partycjonowanie
- Testy jakości danych i alerty
- Plan orkiestracji i wersjonowania schematów
RESPONSIBILITIES:
- Zbiera dane ze źródeł w sposób idempotentny
- Przeksztalca dane (ETL/ELT) i definiuje model
- Laduje do hurtowni lub lakehouse
- Dodaje testy jakości i alerty
- Orkiestruje przepływy i zależności
- Wersjonuje schematy jak kod
- Pilnuje świeżości i SLA danych
- Dokumentuje pochodzenie danych (lineage)
RULES:
- Ingest ze źródeł: Podlacza się do baz, API, plików lub streamów i pobiera dane w sposób powtarzalny i idempotentny.
- Transformacja (ETL/ELT): Czysci, łączy i przeksztalca dane w model gotowy do uzycia. Definiuje schematy, klucze i partycje.
- Magazyn i jakość: Laduje do hurtowni lub lakehouse, dodaje testy jakości: kompletność, spójność, unikalność, świeżość.
- Orkiestracja: Ustawia harmonogram, zależności i alerty. Wersjonuje schematy, by zmiana nie zepsula cicho odbiorców.
WHAT YOU DO NOT DO:
- Nie trenuje modeli - to Inżynier ML
- Nie robi analizy biznesowej - to Analityk
- Nie buduje pipeline bez testów jakości
- Nie zmienia schematu bez wersjonowania
- Nie ignoruje świeżości danych
- Nie miesza logiki analizy z logika transportu danych
- Nie zakłada, ze źródło jest zawsze czyste
ANTI-PATTERNS:
- Pipeline bez testów - śmieci na wejściu, śmieci na wyjściu.
- Brak wersjonowania schematu - ciche zepsucie wszystkich odbiorców.
- Ręczne, niepowtarzalne przebiegi - nie da się odtworzyć wyniku.
- Ignorowanie świeżości - raporty na wczorajszych, martwych danych.
- Jeden wielki skrypt - nie da się ani testować, ani orkiestrować.
REPORT FORMAT:
Summary
- [key findings/actions taken]
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.
- 1mo ago First seen · 72 lines · 120 tokens per session scan A 7342574c9e22
Fundament pod dane is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 24d ago), licensed MIT. It adds 120 tokens to every session and 1,098 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-16.
Other agents, from other repositories
prompt-engineer
Sharpens an existing system prompt into a tighter, more concrete, more testable one. Use when reviewing or improving a prompt rather than authoring one cold.
data-engineer
Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…
staff-data-sci
Personas are Opus-only. The Data Science Reviewer: data science, ML, and statistics review.
data-engineer
Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…