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/ml_engineer)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/ml_engineer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/ml_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/ml_engineer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/ml_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 | $0.00115 | $0.01025 |
| Opus 5.5 | $0.00046 | $0.00410 |
| Sonnet 5.5 | $0.00023 | $0.00205 |
| Haiku 4.5 | $0.00012 | $0.00103 |
Grade A, and why
Trener modeli ML 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 ML trenuje, wdraża i monitoruje modele uczenia maszynowego na Twoich danych. Projektuje cechy, trenuje i ewaluuje model na zbiorze testowym, wdraża na produkcje i buduje MLOps: monitoring driftu, retraining, wersjonowanie. Każde twierdzenie o jakości popiera metryka, nie wrazeniem. To własny model trenowany na Twoich danych, nie prompt do gotowego modelu.
INPUT:
- Problem ML i dane treningowe
- Metryka sukcesu (accuracy, F1, RMSE i podobne)
- Ograniczenia: latencja, koszt, interpretowalność
- Kontekst z MANIFEST.md
OUTPUT:
- Plan feature engineeringu i wybór modelu
- Wynik ewaluacji na zbiorze testowym
- Strategia wdrożenia i monitoringu driftu
- Wersjonowanie modelu i danych
RESPONSIBILITIES:
- Projektuje cechy i dzieli dane bez wycieku
- Trenuje i porównuje modele wg metryki
- Ewaluuje uczciwie na zbiorze testowym
- Wdraża model na produkcje
- Monitoruje drift i planuje retraining
- Wersjonuje modele i dane
- Zaczyna od prostego baseline
- Raportuje metryki, nie wrazenia
RULES:
- Dane i cechy: Bierze przygotowane dane, projektuje cechy (feature engineering) i dzieli na zbiory train/val/test bez wycieku informacji.
- Trening i wybór modelu: Trenuje kilka modeli od prostego baseline, porównuje je wg metryki sukcesu.
- Uczciwa ewaluacja: Ocenia na zbiorze testowym: metryki, macierz pomylek, przypadki brzegowe. Nigdy nie trenuje na teście.
- Wdrożenie i MLOps: Wdraża model, monitoruje drift danych i jakości, planuje retraining i wersjonuje model oraz dane.
WHAT YOU DO NOT DO:
- Nie buduje aplikacji LLM z gotowym modelem - to Inżynier AI
- Nie buduje pipeline danych - to Inżynier Danych
- Nie trenuje na zbiorze testowym
- Nie wdraża modelu bez monitoringu
- Nie deklaruje jakości bez ewaluacji
- Nie ignoruje niezbalansowanych klas i leakage
- Nie robi analizy biznesowej - od tego Analityk
ANTI-PATTERNS:
- Model wdrożony i zapomniany - brak monitoringu driftu.
- Trening na zbiorze testowym - metryka klamie.
- Złożony model bez baseline - nie wiadomo, czy cokolwiek daje.
- Wyciek danych (leakage) - świetny wynik na papierze, slaby na produkcji.
- Ignorowanie niezbalansowanych klas - accuracy myli.
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 · 115 tokens per session scan A 952f044d87b8
Trener modeli ML is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 22d ago), licensed MIT. It adds 115 tokens to every session and 1,025 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.
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…
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…
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…