paper-claim-audit

paper-claim-audit is a skill for Claude Code from wanshuiyin/Auto-claude-code-research-in-sleep. It costs 77 tokens per session (3,585 once invoked), scanned A, original, MIT.

A zero-context check that compares the numbers, comparisons, and scope statements in a paper with the raw experiment result files. It uses a fresh reviewer that has not seen the earlier research process.

In plain words
What is it for?
Use it before submitting a research paper to verify reported metrics, percentage improvements, comparisons, and experiment scope. It checks whether each claim is supported by the underlying result files.
Why use it?
It helps catch incorrect rounding, mismatched experiment settings, cherry-picked results, and claims that overstate the evidence. The reviewer’s lack of prior context reduces the risk of simply confirming the author’s expectations.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; 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 before submitting a research paper to verify reported metrics, percentage improvements, comparisons, and experiment scope. It checks whether each claim is supported by the underlying result files.

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 · 16,030 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/paper-claim-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 paper-claim-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit/github.svg)](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-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 paper-claim-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,585 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 $0.00077 $0.03585
Opus 5 $0.00039 $0.01792
Sonnet 5 $0.00015 $0.00717
Haiku 4.5 $0.00008 $0.00359

Measured 5d ago against content hash 7a6e76d6355a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

paper-claim-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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/paper-claim-audit/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Claim Audit: Zero-Context Evidence Verification

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is verdict-bearing — it judges paper-to-evidence fidelity with a deliberately zero-context fresh reviewer. Re-firing that verdict on a wall-clock timer adds no new signal (it changes only when the paper or results change). Schedule the external wait that precedes it — paper draft ready → then audit once. See shared-references/external-cadence.md.

Verify that every claim in the paper matches raw evidence for: $ARGUMENTS

Why This Exists

The executor writes experiments AND writes the paper. It "knows" what the results should be. This creates confirmation bias:

  • Rounding 84.7% up to 85.3%
  • Reporting best seed instead of average
  • Citing metrics from a different experiment config
  • Claiming "improves by 15%" when the delta is actually 12.8%

A fresh reviewer with zero prior context catches these because it has no expectations — it just compares paper text vs raw files.

How This Differs From Other Audit Skills

Skill Question it answers
/experiment-audit Is the experiment code honest? (fake GT, normalization fraud)
/result-to-claim Does the data scientifically support this claim?
/paper-claim-audit Does the paper report the data truthfully and precisely?

Core Principle

Zero-context, fresh reviewer. The auditor receives ONLY:

  • Paper .tex files (the claims)
  • Raw result files (the evidence)

It does NOT receive:

  • ❌ EXPERIMENT_LOG.md
  • ❌ EXPERIMENT_TRACKER.md
  • ❌ AUTO_REVIEW.md
  • ❌ NARRATIVE_REPORT.md
  • ❌ Any executor summary or interpretation
  • ❌ Any prior audit results
  • ❌ Any conversation history

This is stricter than reviewer-independence — it's zero-context evidence audit.

Workflow

Step 1: Collect Files (Executor — Claude)

Locate paper and result files WITHOUT reading or interpreting them.

Read the full file on GitHub · 349 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. 5d ago Changed 7a6e76d6355a
  2. 13d ago First seen · 349 lines · 77 tokens per session scan A 7cf2a3659a0d

Subscribe to this mod's changes

paper-claim-audit is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (16,030 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 3,585 once invoked, about $0.0004 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

remote-compute-ssh

Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.

aipoch/open-science · 53 tokens

paper-narrative

Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a grounded brief from the manuscript and captions, review the full deck as a handling editor, and hand an ordered figure arc to figure-composer.

aipoch/open-science · 58 tokens

scvi-tools

Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…

aipoch/open-science · 100 tokens

esmfold2

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…

aipoch/open-science · 223 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

openfold3

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.

aipoch/open-science · 60 tokens