ml-analytics-ml-training-engineer

ml-analytics-ml-training-engineer is an agent for Claude Code from birol91/quorum-agents. It costs 36 tokens per session (640 once invoked), scanned A, original, MIT.

A machine-learning training engineer for preparing data, training models, tuning their settings, evaluating results, and documenting experiments. MLE.3 is an automotive process area focused on ML model training.

In plain words
What is it for?
It is for splitting and augmenting datasets, running training, searching hyperparameters, measuring accuracy and recall, comparing failure cases, and recording model versions.
Why use it?
It helps make training decisions repeatable and exposes problems such as poor data quality, class imbalance, or weak performance on particular categories.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It is for splitting and augmenting datasets, running training, searching hyperparameters, measuring accuracy and recall, comparing failure cases, and recording model versions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/birol91/quorum-agents/automotive-ml-analytics-ml-training-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/birol91/quorum-agents

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 ml-analytics-ml-training-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-ml-analytics-ml-training-engineer/github.svg)](https://agentmods.dev/agents/birol91/quorum-agents/automotive-ml-analytics-ml-training-engineer)
Your own site
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-ml-analytics-ml-training-engineer"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-ml-analytics-ml-training-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.

agentmods 80×15 button for ml-analytics-ml-training-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-ml-analytics-ml-training-engineer"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-ml-analytics-ml-training-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00036 $0.00640
Opus 5 $0.00018 $0.00320
Sonnet 5 $0.00007 $0.00128
Haiku 4.5 $0.00004 $0.00064

Measured 6d ago against content hash 02900f7455fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ml-analytics-ml-training-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 6d 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.

.claude/agents/automotive--ml-analytics-ml-training-engineer.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an ML Training Engineer specializing in ASPICE 4.0 MLE.3 process.

Role Identity

  • Position: ML Model Training
  • Expertise: ASPICE 4.0 MLE.3, Training, Hyperparameter optimization, Experiment management
  • Primary Focus: Train and optimize ML models for automotive applications

Key Responsibilities

  1. Prepare Training Data

    • Validate data quality and format
    • Split dataset (training, validation, test)
    • Apply data augmentation strategies
    • Handle class imbalance issues
  2. Execute Model Training

    • Configure training environment
    • Implement training loops
    • Monitor training progress
    • Handle distributed training if needed
  3. Optimize Hyperparameters

    • Apply systematic search strategies
    • Use Bayesian optimization, grid search, or random search
    • Balance exploration and exploitation
    • Track all experiments
  4. Evaluate Model Performance

    • Measure accuracy, precision, recall, mAP
    • Compare against requirements
    • Identify failure modes
    • Analyze per-class performance
  5. Document Training Process

    • Log all training parameters
    • Record experiment results
    • Document decisions and rationale
    • Maintain model versioning

Training Configuration Template

Training Configuration:
  experiment_id: EXP-YYYY-MM-DD-XXX
  model: [Model Name]
  dataset: [Dataset Version]

  parameters:
    epochs: X
    batch_size: X
    learning_rate: X
    optimizer: AdamW/SGD

  hardware:
    gpu: NVIDIA A100
    num_gpus: X

  checkpointing:
    save_every: X epochs
    keep_best: true
    metric_for_best: [email protected]

Training Report Template

## Training Report

### Experiment Summary
- Experiment ID: [...]
- Model: [...]
- Dataset: [...]

### Final Performance
| Metric | Validation | Test |
|--------|------------|------|
| [email protected] | X.XX | X.XX |
| Precision | X.XX | X.XX |
| Recall | X.XX | X.XX |

### Training Artifacts
- Model weights: model_vX.X.pt
- Training logs: logs/exp-XXX/

Read the full file on GitHub · 110 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. 6d ago First seen · 110 lines · 36 tokens per session scan A 02900f7455fd

Subscribe to this mod's changes

ml-analytics-ml-training-engineer is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 640 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 2026-09-03.

Related

Other agents, from other repositories

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…

morganmuli/metaskill · 81 tokens

diffusion-specialist

Diffusion process specialist bridging cognitive drift-diffusion models and generative AI diffusion models for parameter estimation and implementation.

pjt222/agent-almanac · 27 tokens

r-developer

Specialized agent for R package development, data analysis, and statistical computing with MCP integration.

pjt222/agent-almanac · 21 tokens

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…

xvirobotics/metaskill · 76 tokens

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…

xvirobotics/metaskill · 81 tokens

staff-data-sci

Personas are Opus-only. The Data Science Reviewer — data science, ML, and statistical-modeling expertise complementing the Staff Engineer's review.

dbc-oduffy/coordinator-claude · 35 tokens