ml-experiment-tracker

ml-experiment-tracker is a skill for Claude Code, Codex from khalilbenaz/claude-skills-collection. It costs 122 tokens per session (2,008 once invoked), scanned A, original, MIT.

A guide for recording and comparing machine-learning training experiments. It tracks each run's settings, measurements, files, and model versions using tools such as MLflow, Weights & Biases, Neptune, or ClearML.

In plain words
What is it for?
Naming and tagging training runs, recording datasets and parameters, comparing metrics, storing training files, and maintaining versions in a model registry.
Why use it?
It removes the guesswork of remembering which data, settings, and code produced a result. This makes it easier to compare approaches and keep the best models identifiable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/check_metrics.py \.

Good fit Naming and tagging training runs, recording datasets and parameters, comparing metrics, storing training files, and maintaining versions in a model registry.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/khalilbenaz/claude-skills-collection
agentmods
npx agentmods add skills/khalilbenaz/claude-skills-collection/ml-experiment-tracker

Made for: Claude Code, Codex.

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 ml-experiment-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/ml-experiment-tracker/github.svg)](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/ml-experiment-tracker)
Your own site
<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.

agentmods 80×15 button for ml-experiment-tracker

Your own site · 80×15
<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>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,008 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00122 $0.02008
Opus 5 $0.00061 $0.01004
Sonnet 5 $0.00024 $0.00402
Haiku 4.5 $0.00012 $0.00201

Measured 11d ago against content hash 5f407f61678c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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(
ai-ml-skills/ml-experiment-tracker/SKILL.md · 238 lines

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 DVC
  • model_type : lgbm, resnet50, bert-base, …
  • env : dev / staging / prod
  • owner : 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()

Read the full file on GitHub · 238 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. 11d ago First seen · 238 lines · 122 tokens per session scan A 5f407f61678c

Subscribe to this mod's changes

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.