CATHERINE: Agent for Claude Code

.claude/agents/senior-machine-learning-engineer.agent.md

senior-machine-learning-engineer is an agent for Claude Code from Jm-Paunlagui/CATHERINE. It costs 105 tokens per session (901 once invoked), scanned A, original, Apache-2.0.

A specialist for building, reviewing, and fixing classical and tabular machine-learning systems. It focuses on models trained from rows and columns of data rather than foundation-model applications.

In plain words
What is it for?
Use it for feature selection, model training, cross-validation, metric choice, class imbalance, leakage checks, and diagnosing overfitting in tabular data.
Why use it?
It helps prevent data leakage, misleading accuracy scores, overfitting, poor handling of imbalanced classes, and transformations applied to the wrong data.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Jm-Paunlagui/CATHERINE's own configuration. It tells Claude Code how to work on CATHERINE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CATHERINE configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/agents/senior-machine-learning-engineer.agent.md
Clone the repo
git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

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 senior-machine-learning-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-machine-learning-engineer.svg)](https://agentmods.dev/agents/jm-paunlagui/catherine/senior-machine-learning-engineer)
Your own site
<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>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 901 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 $0.00105 $0.00901
Opus 5 $0.00053 $0.00451
Sonnet 5 $0.00021 $0.00180
Haiku 4.5 $0.00011 $0.00090

Measured 2d ago against content hash 15efd6080646, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

.claude/agents/senior-machine-learning-engineer.agent.md · 43 lines

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

  1. 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.
  2. 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.
  3. Run the five-way leakage sweep: target, train-test contamination, temporal, group, and tuning leakage. Encapsulate every transform in a Pipeline / ColumnTransformer so it fits inside the fold.
  4. Engineer features as-of prediction time. Anything only knowable after the label is a defect.
  5. Pick the metric from the decision and the cost matrix, not from habit. Calibrate when the probability itself is consumed.
  6. Start with a regularised linear baseline and gradient boosting; justify anything heavier against a tuned GBM. Early-stop on validation.
  7. Record seeds, the split definition, data version, and environment. A result you cannot reproduce is a claim.

Read the full file on GitHub · 43 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. 2d ago First seen · 43 lines · 105 tokens per session scan A 15efd6080646

Subscribe to this mod's changes

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.

Related

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.

github/awesome-copilot · 24 tokens

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.

github/awesome-copilot · 56 tokens

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".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

mlops-engineer

ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.

pjt222/agent-almanac · 31 tokens

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.

ahmedawan-oracle/claude-code-plugins · 70 tokens

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.

jkitchin/discopt · 59 tokens