Experiment Tracking

Experiment Tracking is a skill for Claude Code, Codex from niels-emmer/myace. It costs 27 tokens per session (327 once invoked), scanned A, original, MIT.

A guide for recording machine-learning experiments so their settings, results, files, and software environment can be reproduced. An experiment is a documented training or data-processing run.

In plain words
What is it for?
Use it to name runs, log parameters and metrics, save model outputs and plots, record the environment, compare runs, and reproduce a previous result.
Why use it?
It prevents results from becoming impossible to explain or repeat because important settings, random seeds, data choices, or software versions were not recorded.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: mentions Codex; built for aider; mentions OpenCode.

Good fit Use it to name runs, log parameters and metrics, save model outputs and plots, record the environment, compare runs, and reproduce a previous result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/niels-emmer/myace/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 niels-emmer/myace --skill experiment-tracking
Clone the repo
git clone --depth 1 https://github.com/niels-emmer/myace

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/niels-emmer/myace/experiment-tracking/github.svg)](https://agentmods.dev/skills/niels-emmer/myace/experiment-tracking)
Your own site
<a href="https://agentmods.dev/skills/niels-emmer/myace/experiment-tracking"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/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/niels-emmer/myace/experiment-tracking"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/experiment-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 327 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00027 $0.00327
Opus 5 $0.00014 $0.00163
Sonnet 5 $0.00005 $0.00065
Haiku 4.5 $0.00003 $0.00033

Measured 9d ago against content hash 3d1838b272a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Experiment Tracking 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 9d 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.

collections/base/data-scientist/skills/experiment-tracking/SKILL.md · 31 lines

What it actually says

Purpose

Ensure every experiment is reproducible from its logged state alone.

When to use it

Every training run, every data transformation, every evaluation.

Checklist

  • Run naming: {date}-{objective}-{attempt} (e.g. 2026-08-12-classifier-lr-search-03).
  • Seed everything: numpy, python random, torch, tensorflow — log which seeds were used.
  • Log parameters: hyperparameters, data splits, preprocessing choices, model architecture.
  • Log metrics: final metrics per split (train/val/test), per-epoch metrics if relevant.
  • Log artifacts: model weights, predictions, feature importance plots, confusion matrices.
  • Log environment: Python version, dependency versions (lockfile or pip freeze), git commit hash.
  • Compare runs: use the tracker's comparison view or export to a structured format.
  • Recover: from a logged run, you should be able to reproduce the exact result.

Expected output

A tracked run that another person or agent can reproduce without asking the original author for details.

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. 9d ago First seen · 31 lines · 27 tokens per session scan A 3d1838b272a0

Subscribe to this mod's changes

Experiment Tracking is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 327 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

histolab

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

synthetic-sciences/openscience · 62 tokens

pyhealth

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…

synthetic-sciences/openscience · 109 tokens

deepchem

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…

synthetic-sciences/openscience · 78 tokens

torch-geometric

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

synthetic-sciences/openscience · 41 tokens

zarr-python

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

synthetic-sciences/openscience · 42 tokens

alphafold-database

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

synthetic-sciences/openscience · 54 tokens