experiment-audit

experiment-audit is a skill for Claude Code from wanshuiyin/Auto-claude-code-research-in-sleep. It costs 70 tokens per session (3,097 once invoked), scanned A, original, MIT.

A review step that checks whether an experiment's reported results are supported by real data and a sufficiently broad test.

In plain words
What is it for?
Use it after an experiment to check the honesty and scope of its results before presenting them.
Why use it?
It helps catch made-up reference data, misleading score calculations, results from code that never ran, and claims based on tests that were too small.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [`shared-references/external-cadence.md`](../shared-references/external-cadence.md)..

Good fit Use it after an experiment to check the honesty and scope of its results before presenting them.

Compare 6 skills from other repositories ↓
About the project

ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.

wanshuiyin/Auto-claude-code-research-in-sleep · 15,970 stars · on GitHub

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/wanshuiyin/Auto-claude-code-research-in-sleep
agentmods
npx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/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/skills/wanshuiyin/auto-claude-code-research-in-sleep/experiment-audit/github.svg)](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/experiment-audit)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/experiment-audit"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/experiment-audit/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-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/experiment-audit"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/experiment-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,097 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. Third-party audits
  • Socket pass 18 May 2026
  • Snyk pass 18 May 2026
  • 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 $0.00070 $0.03097
Opus 5 $0.00035 $0.01548
Sonnet 5 $0.00014 $0.00619
Haiku 4.5 $0.00007 $0.00310

Measured 4d ago against content hash dd5c2405aaae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

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 4d 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.

skills/experiment-audit/SKILL.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment Audit: Cross-Model Integrity Verification

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is verdict-bearing — it judges experiment integrity. Re-running that verdict on a timer adds no new signal, and a loop that accepts its own output to decide when to stop crosses into self-acquittal (acceptance-gate.md). Schedule the external wait that precedes it — experiments done → then audit once. See shared-references/external-cadence.md.

Audit experiment integrity for: $ARGUMENTS

Why This Exists

LLM agents can produce fraudulent experimental results through:

  1. Fake ground truth — creating synthetic "reference" from model outputs, then reporting high agreement as performance
  2. Score normalization — dividing metrics by the model's own max to get 0.99+
  3. Phantom results — claiming numbers from files that don't exist or functions never called
  4. Insufficient scope — reporting 2-scene pilots as "comprehensive evaluation"

These are NOT intentional deception — they are failure modes of optimizing agents that lack integrity constraints. This skill adds that constraint.

Core Principle

The executor collects file paths. The external reviewer backend reads code and judges integrity. The executor does NOT participate in integrity judgment.

This follows shared-references/reviewer-independence.md and shared-references/experiment-integrity.md.

Constants

  • REVIEWER_BACKEND = codex — Default: Codex MCP (ultra). Override with — reviewer: oracle-pro for Oracle MCP, or — reviewer: manual for Manual Review MCP. If manual-review MCP is unavailable, stop and print the install command; do not fall back to Codex. See shared-references/reviewer-routing.md.

Reviewer Calling Convention

When calling the reviewer, branch on REVIEWER_BACKEND:

If REVIEWER_BACKEND = codex: Use mcp__codex__codex for new review threads. Use mcp__codex__codex-reply for follow-up rounds (reuse threadId).

Read the full file on GitHub · 312 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. 4d ago Changed dd5c2405aaae
  2. 12d ago First seen · 312 lines · 70 tokens per session scan A 476bde891323

Subscribe to this mod's changes

experiment-audit is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (15,970 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 3,097 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

write-experiment-code

Produce the experiment code in an AIRAS experiment repository — against the execution contract stated here and the airas-eval input schema, with the environment fixed by lockfile and Dockerfile. Use to write, fix, or regenerate experiment code, whether authored directly or via an external code-generation tool.

airas-org/airas · 64 tokens

train-pose

Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.

ruvnet/RuView · 44 tokens

i4h-catheter-navigation-e2e

End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.

NVIDIA/skills · 49 tokens

i4h-catheter-navigation-render-drr

Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.

NVIDIA/skills · 48 tokens

figure-style

Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…

aipoch/open-science · 91 tokens

literature-review

Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.

aipoch/open-science · 54 tokens