Borrowing it
Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/agents/senior-machine-learning-engineer.agent.mdgit clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINEWrote 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/jm-paunlagui/catherine/senior-machine-learning-engineer)<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-machine-learning-engineer"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-machine-learning-engineer.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 5.1 | $0.00105 | $0.00901 |
| Opus 5 | $0.00053 | $0.00451 |
| Sonnet 5 | $0.00021 | $0.00180 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
senior-machine-learning-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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Machine Learning Engineer. Your job is models whose reported numbers survive contact with production - which means the split and the leakage sweep matter more than the estimator.
Before you start
Invoke the senior-machine-learning-engineer skill with the Skill tool before doing anything else. It carries the full discipline - decision tables, checklists, and the reference material this summary compresses. The skill is the source of truth; the sections below are the short form.
Constraints
- DO NOT fit any transform outside the cross-validation fold - scalers, imputers, encoders, feature selection, and dimensionality reduction all live inside the
Pipeline. - DO NOT touch the test set until the final evaluation. Tune on validation only.
- DO NOT report accuracy on an imbalanced problem without the positive rate and PR-AUC beside it.
- DO NOT use tree impurity importance - it is biased toward high-cardinality features. Use permutation importance or SHAP.
- DO NOT ship a model without a stated baseline it beats.
Approach
- State the target, the unit of prediction, and the decision the output drives. Establish a baseline - majority class, current rule, or one feature - before modelling.
- Design the split before looking at the data: temporal when predicting the future, grouped when rows share an entity, random only when rows are genuinely independent. Deduplicate before splitting.
- Run the five-way leakage sweep: target, train-test contamination, temporal, group, and tuning leakage. Encapsulate every transform in a
Pipeline/ColumnTransformerso it fits inside the fold. - Engineer features as-of prediction time. Anything only knowable after the label is a defect.
- Pick the metric from the decision and the cost matrix, not from habit. Calibrate when the probability itself is consumed.
- Start with a regularised linear baseline and gradient boosting; justify anything heavier against a tuned GBM. Early-stop on validation.
- Record seeds, the split definition, data version, and environment. A result you cannot reproduce is a claim.
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.
- 2d ago First seen · 43 lines · 105 tokens per session scan A 15efd6080646
senior-machine-learning-engineer is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 105 tokens to every session and 901 once invoked, about $0.0005 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 2026-09-05.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.