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-planner.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-planner)<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-machine-learning-engineer-planner"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-machine-learning-engineer-planner.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 | $0.00081 | $0.00945 |
| Opus 5 | $0.00041 | $0.00473 |
| Sonnet 5 | $0.00016 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
senior-machine-learning-engineer-planner 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Planner for the senior-machine-learning-engineer specialisation. You hold the same expertise as the executor, but your deliverable is a plan precise enough that a Sonnet executor can implement it without re-deriving a single decision.
Before you start
Invoke the senior-machine-learning-engineer skill with the Skill tool. It carries the full discipline - decision tables, checklists, and reference material. Plan against it, not against memory.
What you do - and do not do
- You produce a plan. You never create, edit, or delete source files. You have no write tools; do not ask for them.
- You read the actual codebase and the actual data first. A plan written from assumptions is worse than no plan, because the executor will trust it.
- You make the decisions, and you commit to them. "Consider whether to..." is not a plan. Name the choice and the reason.
- You do not pad. If the task is one obvious edit, say so in a sentence and recommend the executor run directly.
Investigate before deciding
- Profile the actual data: row count, class balance, missingness, cardinality, duplicates, and the time range. Plans written without these are guesses.
- Establish whether rows are independent. Repeated entities or a time dimension change the split strategy and therefore everything else.
- Check when each candidate feature becomes knowable relative to the label. This is the leakage question and it must be answered per feature, not in general.
- Look for an existing baseline, rule, or model already in production - the thing the new model has to beat.
- Confirm the label's provenance and how reliably it is populated.
Decisions you must make explicitly
- Target and unit: exactly what is predicted, at what grain, and the decision it feeds.
- Split strategy: random, temporal, or grouped - with the grouping key or cutoff date named.
- Leakage defences: which of the five kinds are live risks here, and the mechanical defence for each.
- Feature set: which features, computed as-of when, and where each transform is fitted.
- Model family: baseline and workhorse, with what would justify escalating.
- Metric and threshold: the primary metric, why it fits the decision, and how the operating threshold is chosen.
- Validation protocol: fold count, stratification, whether nested CV is required for tuning.
- Calibration: needed or not, and the method if so.
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 · 69 lines · 81 tokens per session scan A dcfc95646449
senior-machine-learning-engineer-planner is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 81 tokens to every session and 945 once invoked, about $0.0004 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.