experiment-tracking

experiment-tracking is a skill for Claude Code, Codex from sawrus/agent-guides. It costs 0 tokens per session (233 once invoked), scanned A, original, MIT.

A way to record the settings, data versions, results, code revisions, and saved files from machine-learning training runs using MLflow.

In plain words
What is it for?
Use it while training models, comparing runs, recording metrics and parameters, linking runs to Git commits, and saving evaluation files.
Why use it?
It makes experiments easier to compare and reproduce, so you can understand which changes produced a result and recreate an earlier model.

Skill for Claude CodeCodex

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

Good fit Use it while training models, comparing runs, recording metrics and parameters, linking runs to Git commits, and saving evaluation files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sawrus/agent-guides/experiment-tracking
Install

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.

Any agent
npx skills add sawrus/agent-guides --skill experiment-tracking
Clone the repo
git clone --depth 1 https://github.com/sawrus/agent-guides

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 experiment-tracking

README.md
[![agentmods](https://agentmods.dev/badge/skills/sawrus/agent-guides/experiment-tracking/github.svg)](https://agentmods.dev/skills/sawrus/agent-guides/experiment-tracking)
Your own site
<a href="https://agentmods.dev/skills/sawrus/agent-guides/experiment-tracking"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/experiment-tracking/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 experiment-tracking

Your own site · 80×15
<a href="https://agentmods.dev/skills/sawrus/agent-guides/experiment-tracking"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/experiment-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 233 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 $0.00000 $0.00233
Opus 5 $0.00000 $0.00117
Sonnet 5 $0.00000 $0.00047
Haiku 4.5 $0.00000 $0.00023

Measured 6d ago against content hash ae6d5dcd97e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

experiment-tracking 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 6d 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.

"git_commit": subprocess.check_output(["git", "rev-parse", "HEAD"]).decode().strip(),
areas/software/mlops/skills/experiment-tracking/SKILL.md · 30 lines

What it actually says

Skill: Experiment Tracking (MLflow)

When to load

When running training experiments, comparing runs, or reproducing a historical experiment.

MLflow Tracking Pattern

with mlflow.start_run(run_name="xgboost-lr-0.01-depth-6") as run:
    mlflow.log_params({
        "model_type": "xgboost",
        "learning_rate": 0.01,
        "max_depth": 6,
        "data_version": dataset_version,
        "random_seed": 42,
    })
    mlflow.set_tags({
        "git_commit": subprocess.check_output(["git", "rev-parse", "HEAD"]).decode().strip(),
    })

    model = train_model(X_train, y_train, hyperparams)

    mlflow.log_metrics({"test_auc_roc": 0.847, "test_f1": 0.731})

    signature = mlflow.models.infer_signature(X_train, model.predict(X_train))
    mlflow.xgboost.log_model(model, "model", signature=signature)
    mlflow.log_artifact("evaluation_scorecard.json")
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. 6d ago First seen · 30 lines · 0 tokens per session scan A ae6d5dcd97e0

Subscribe to this mod's changes

experiment-tracking is a skill published in the GitHub repository sawrus/agent-guides (17 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 233 tokens. 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 2026-09-03.