experiment-audit

experiment-audit is a plugin for Claude Code from SreeDharshan-GJ/experiment-audit. Its manifest loads nothing; the 1 skill it bundles cost 276 tokens per session together, scanned A, original, MIT.

A research-analysis add-on for evaluating scientific and machine-learning experiments, papers, and empirical claims. It can optionally connect to Weights & Biases, a service for tracking machine-learning experiments.

In plain words
What is it for?
Auditing training runs, ablation studies, experiment sweeps, papers, and reproducibility, with structured research reports.
Why use it?
It helps check whether conclusions match the evidence, whether results can be reproduced, and whether comparisons or statistical claims are sound.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add SreeDharshan-GJ/experiment-audit
agentmods
npx agentmods add plugins/sreedharshan-gj/experiment-audit/experiment-audit-plugin
Clone the repo
git clone --depth 1 https://github.com/SreeDharshan-GJ/experiment-audit

Made for: Claude Code.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/plugins/sreedharshan-gj/experiment-audit/experiment-audit-plugin.svg)](https://agentmods.dev/plugins/sreedharshan-gj/experiment-audit/experiment-audit-plugin)
Your own site
<a href="https://agentmods.dev/plugins/sreedharshan-gj/experiment-audit/experiment-audit-plugin"><img src="https://agentmods.dev/badge/plugins/sreedharshan-gj/experiment-audit/experiment-audit-plugin.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 276 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

experiment-audit 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 5d 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.

dev/experiment-audit-plugin/.claude-plugin/plugin.json · 21 lines

What it actually says

{
  "name": "experiment-audit",
  "version": "1.1.0",
  "description": "Scientific Research Reasoning Engine for evaluating experimental and empirical claims — auditing ML training runs, ablations, and sweeps; reviewing papers; checking reproducibility; and producing structured research reports. Optional Weights & Biases integration via the experiment-audit-mcp server.",
  "author": {
    "name": "Experiment Audit Project"
  },
  "keywords": [
    "science",
    "research",
    "machine-learning",
    "experiment-tracking",
    "wandb",
    "statistics",
    "reproducibility",
    "peer-review",
    "reasoning-engine"
  ],
  "license": "MIT"
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 276 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json 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.

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. 5d ago First seen · 21 lines scan A 4610907e8d84

Subscribe to this mod's changes

experiment-audit is a plugin published in the GitHub repository SreeDharshan-GJ/experiment-audit (7 stars, last pushed 10d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.

Related

Other plugins, from other repositories

tidymodels-developers

Development tools and guides for tidymodels ecosystem packages including yardstick metrics, recipes steps, dials parameters, and parsnip models.

tidymodels/skills · not measured

animal-geneticist-breeder

Reasons from additive genetic variance, response to selection (R = i h sigmaA), accuracy, and inbreeding depression through REML/BLUP and ssGBLUP pipelines (BLUPF90, ASReml, WOMBAT), economic selection indices, optimum-contribution mate allocation, and Interbull MACE while treating confounded contemporary groups, pred.

K-Dense-AI/scientific-agents · not measured

antimicrobial-resistance-scientist

Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim…

K-Dense-AI/scientific-agents · not measured

catalysis-scientist

Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator…

K-Dense-AI/scientific-agents · not measured

climate-scientist

Reasons from ERF/EEI energy-budget closure, AR6 forcing (WMGHG vs ERFaci), optimal fingerprinting and FAR event attribution, CMIP6/ScenarioMIP SSP workflows (ESGF, ESMValTool), and paleo proxy physics (PAGES2k, ice-core δD/CO₂, foraminifera Mg/Ca, coral Sr/Ca) while treating aerosol uncertainty, tree-ring divergence…

K-Dense-AI/scientific-agents · not measured

agricultural-engineer

Reasons from mass, energy, and momentum balances on variable biological media through ET-based scheduling, psychrometric grain-drying balances, ASABE D497 draft estimates, EPANET pipe networks, and RTK-GNSS/ISOBUS precision-ag validation while treating soil compaction, clogged drip emitters, grain-bin hotspots, GPS…

K-Dense-AI/scientific-agents · not measured