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.
npx skills add NeoXider/neoxider-mcp-hub --skill ml-experiment-reviewgit clone --depth 1 https://github.com/NeoXider/neoxider-mcp-hubWrote 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/skills/neoxider/neoxider-mcp-hub/ml-experiment-review)<a href="https://agentmods.dev/skills/neoxider/neoxider-mcp-hub/ml-experiment-review"><img src="https://agentmods.dev/badge/skills/neoxider/neoxider-mcp-hub/ml-experiment-review/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/skills/neoxider/neoxider-mcp-hub/ml-experiment-review"><img src="https://agentmods.dev/badge/skills/neoxider/neoxider-mcp-hub/ml-experiment-review.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 | $0.00000 | $0.00142 |
| Opus 5 | $0.00000 | $0.00071 |
| Sonnet 5 | $0.00000 | $0.00028 |
| Haiku 4.5 | $0.00000 | $0.00014 |
Grade A, and why
ml-experiment-review 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 12d 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.
What it actually says
ML Experiment Review
Use this skill when reviewing an ML experiment, benchmark, ablation, or training run.
- State the hypothesis in falsifiable form.
- Identify the baseline, treatment, controlled variables, dataset split, seeds, and stopping rule.
- Separate observed measurements from interpretations.
- Check data leakage, train/eval contamination, metric selection, variance, and cherry-picking risks.
- Record the exact code revision, configuration, environment, artifacts, and commands needed to reproduce the result.
- Report uncertainty and failed runs. Do not turn a promising result into a product-readiness claim.
- End with the smallest next experiment that can discriminate between the leading explanations.
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.
- 12d ago First seen · 12 lines · 0 tokens per session scan A b14248fc31ab
ml-experiment-review is a skill published in the GitHub repository NeoXider/neoxider-mcp-hub (1 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 142 tokens. 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 2026-08-31.
Other skills, from other repositories
bio-workbench
A set of rules for running reproducible bioinformatics analyses, which study biological data with software. It uses small self-contained scripts, recorded inputs and outputs, environment details, and version history so results can be repeated.
ml-iterate
Use when the user is stuck, needs ranked next steps, or wants alternatives after initial experiments — "I tried X and got Y, what next?".
ml-experiment
Use when starting, logging, or reviewing ML experiments — maintains a persistent experiment journal with hypotheses, results, and learnings across sessions.
transfer-learn
Fine-tune a REINVENT4 prior model on a focused SMILES dataset (transfer learning). Use when the user wants to train, fine-tune, or adapt a model to a specific chemical series.
cvqnn
Skill for understanding, using, and implementing the Continuous Variable Quantum Neural Network (CVQNN) for binary classification via the CVQNNAlgorithm class, CVSimulator, and CVClassifier. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.
vqc
Skill for understanding, using, and implementing the Variational Quantum Classifier (VQC) for Iris dataset classification with data re-uploading and Parameter Shift Rule via the VQCAlgorithm class. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.