Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionnpx agentmods add skills/khalilbenaz/claude-skills-collection/ml-experiment-trackerWrote 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/khalilbenaz/claude-skills-collection/ml-experiment-tracker)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/ml-experiment-tracker"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/ml-experiment-tracker/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/khalilbenaz/claude-skills-collection/ml-experiment-tracker"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/ml-experiment-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00122 | $0.02008 |
| Opus 5 | $0.00061 | $0.01004 |
| Sonnet 5 | $0.00024 | $0.00402 |
| Haiku 4.5 | $0.00012 | $0.00201 |
Grade A, and why
ml-experiment-tracker scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
mlflow.log_param("dataset_dvc_hash", subprocess.check_output( How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ML Experiment Tracker
Suivi structuré d'expériences ML, versioning de modèles, comparaison de métriques — MLflow, W&B, Neptune, ClearML.
1. Choisir la plateforme
| Outil | Quand choisir |
|---|---|
| MLflow | On-premise, équipe data interne, pas de budget SaaS |
| W&B | Collaboration multi-équipes, visualisations riches, GPU cloud |
| Neptune | Gros volumes de métadonnées, intégration CI/CD fine |
| ClearML | Orchestration complète (pipeline + HPO + registry) |
Installation MLflow (auto-hébergé) :
pip install mlflow
mlflow server \
--backend-store-uri postgresql://user:pass@host:5432/mlflow \
--default-artifact-root s3://mon-bucket/mlflow \
--host 0.0.0.0 --port 5000
Installation W&B (local) :
pip install wandb
wandb login # ou WANDB_API_KEY=xxx en env var
wandb server start # si self-hosted (Weights & Biases Local)
2. Structurer les expériences
Convention de nommage obligatoire avant le premier run :
{projet}/{tâche}/{variante}
ex: churn/lgbm/baseline
churn/lgbm/feat-engineering-v2
fraud/bert/fine-tune-lr3e-5
Tags standards à appliquer sur chaque run :
dataset_version: hash ou tag DVCmodel_type: lgbm, resnet50, bert-base, …env: dev / staging / prodowner: alias du data scientist
3. Logger paramètres et métriques
MLflow :
import mlflow
mlflow.set_tracking_uri("http://mlflow-server:5000")
mlflow.set_experiment("churn/lgbm/baseline")
with mlflow.start_run(run_name="lgbm-lr0.05-depth6"):
mlflow.log_params({
"learning_rate": 0.05,
"max_depth": 6,
"n_estimators": 500,
"dataset_version": "v2.3",
"seed": 42,
})
# ... entraînement ...
mlflow.log_metrics({"val_auc": 0.872, "val_f1": 0.741}, step=epoch)
mlflow.sklearn.log_model(model, "model")
W&B :
import wandb
run = wandb.init(project="churn", name="lgbm-lr0.05", config={
"learning_rate": 0.05, "max_depth": 6, "seed": 42
})
wandb.log({"val_auc": 0.872, "val_f1": 0.741})
wandb.finish()
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.
- 11d ago First seen · 238 lines · 122 tokens per session scan A 5f407f61678c
ml-experiment-tracker is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 122 tokens to every session and 2,008 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
edgartools
Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K…
model-routing-patterns
Multi-model pipelines (Haiku/Sonnet/Opus): cost routing, escalation, fallback chains. Triggers: model routing, Haiku, Sonnet, Opus, escalation, fallback chain.
rag-patterns
RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.
evaluate
Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
json-mode-patterns
Structured JSON output from Claude: tool-use-as-JSON, schema, parsing, partial recovery. Triggers: JSON mode, structured output, schema validation, JSON parsing.