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 agentmods add skills/arbazkhan971/godmode/mlnpx skills add arbazkhan971/godmode --skill mlgit clone --depth 1 https://github.com/arbazkhan971/godmodeWrote 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/arbazkhan971/godmode/ml)<a href="https://agentmods.dev/skills/arbazkhan971/godmode/ml"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/ml.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 | $0.00007 | $0.01077 |
| Opus 5 | $0.00003 | $0.00539 |
| Sonnet 5 | $0.00001 | $0.00215 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
ml 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activate When
/godmode:ml, "train a model", "compare experiments"- "evaluate model", "check for bias", "dataset quality"
- ML-related code detected (training loops, features)
Workflow
1. Experiment Definition
ID: EXP-<YYYY-MM-DD>-<NNN>
Hypothesis: <what you expect and why>
Objective: <metric to optimize>
Baseline: <current best or naive baseline>
Task: classification|regression|ranking|generation
Framework: PyTorch|TensorFlow|scikit-learn|JAX|XGBoost
# Check for ML frameworks
pip list 2>/dev/null | grep -iE "torch|tensorflow|sklearn"
cat requirements.txt 2>/dev/null | grep -iE "torch|tf"
2. Hyperparameter Management
search:
strategy: grid|random|bayesian|hyperband
space:
learning_rate: [1e-5, 1e-4, 1e-3, 1e-2]
batch_size: [16, 32, 64, 128]
dropout: uniform(0.1, 0.5)
hidden_size: [128, 256, 512, 1024]
trials: <total>
IF trials > 50: use Bayesian or Hyperband (not grid). IF search space > 4 dimensions: use random search minimum.
3. Dataset Validation
Total samples: <N>
Split: train=<N>(<pct>%) / val=<N>(<pct>%) / test=<N>
Quality checks:
Missing values: <count per feature>
Duplicates: <count exact duplicates>
Outliers: <count, method used>
Class balance: <ratio of majority/minority>
IF class imbalance > 10:1: use stratified sampling
- class weights or oversampling. IF missing > 5% for any feature: investigate before imputing.
4. Bias Detection
Protected attributes: <gender, race, age, geography>
Per-attribute:
| Attribute | Group | Samples | Accuracy | FPR | FNR |
IF max_group_accuracy - min_group_accuracy > 5%:
FLAG bias. Investigate feature correlations.
IF FNR disparity > 10% across groups:
BLOCK deployment until mitigated.
5. Training and Tracking
Epoch: <current>/<total>
Training loss: <value> (trend: decreasing|plateau)
Validation loss: <value> (trend)
Primary metric: <value> (best: <val> at epoch <N>)
IF val_loss increases 3 consecutive epochs: early stop. IF train_loss << val_loss (gap > 2x): overfitting.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 140 lines · 7 tokens per session scan A c033c7db7961
ml is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 8d ago), licensed MIT. It adds 7 tokens to every session and 1,077 once invoked, about $0.0000 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.
Other skills, from other repositories
LQF_Machine_Learning_Expert_Guide
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
scientific-data-preprocessing
⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization…
plot-styling
This skill should be used when the user asks to "plot data", "make a plot for a paper", "make a publication plot", "create a journal-quality plot", "matplotlib for a figure", "use seaborn", "use plotnine", "use ggplot in Python", "improve plot quality", "style my plot", "clean up my figure", "my matplotlib plot looks…
nlp-pipeline-designer
Conception de pipelines NLP (tokenization, embeddings, NER, sentiment, summarization) — guide opérationnel avec snippets, critères de décision et anti-patterns. Se déclenche avec : \"NLP\", \"traitement du langage\", \"NER\", \"sentiment analysis\", \"text classification\", \"spaCy\", \"HuggingFace\". Se déclenche…
feature-engineering-guide
Techniques de feature engineering pour améliorer les modèles ML. Se déclenche avec "feature engineering", "features", "transformation de données", "encoding", "normalisation", "feature selection", "feature store". Also triggers on "build ML features".