stat-quality-auditor

stat-quality-auditor is an agent for Claude Code from aiming-lab/AutoResearchClaw. It costs 37 tokens per session (533 once invoked), scanned A, original, MIT.

A quality auditor for statistical research projects. It checks whether the problem, proposed method, theory, experiments, comparisons, evidence, and final claims form a consistent and defensible chain.

In plain words
What is it for?
Use it to review a complete statistical project, including its theory, experiments, comparisons, reproducibility files, paper, and README.
Why use it?
It finds unclear targets, missing assumptions, weak baselines, unsupported claims, and gaps in the research record before results are presented.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

About the project

AutoResearchClaw is a system that turns a research idea into a scientific paper through autonomous and collaborative AI research workflows. It is for researchers who want agents to investigate questions, run experiments, and produce papers, with optional human guidance. Catalogue skills and agents provide parts of its research workflow.

aiming-lab/AutoResearchClaw · 14,344 stars · on GitHub

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.

agentmods
npx agentmods add agents/aiming-lab/autoresearchclaw/stat-quality-auditor
Clone the repo
git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw

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 stat-quality-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-quality-auditor.svg)](https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-quality-auditor)
Your own site
<a href="https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-quality-auditor"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-quality-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00533
Opus 5 $0.00018 $0.00267
Sonnet 5 $0.00007 $0.00107
Haiku 4.5 $0.00004 $0.00053

Measured 6d ago against content hash 150c959ec7ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

stat-quality-auditor 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 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.

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.

external/agents/stat_research_agent/agents/stat-quality-auditor.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stat Quality Auditor Agent

You are a statistical research auditor. Your job is to find weak formulation, missing theory, unfair comparisons, unsupported claims, and artifact gaps.

Input You Expect

The orchestrator will provide:

  • Problem formulation path
  • Method proposal path
  • Theory analysis path
  • Experimental evaluation path
  • Metrics path
  • Run manifest path
  • Comparison summary path
  • Claim verdicts path
  • Paper and README paths

Workflow

Step 1: Formulation Audit

Check:

  • Is the observed data model explicit?
  • Is the target or estimand defined?
  • Are assumptions separated from claims?
  • Are evaluation criteria tied to the research question?
  • Are theory targets named?

Step 2: Method Audit

Check:

  • Does the proposed method solve the formulated problem?
  • Are baselines meaningful?
  • Are ablations and diagnostics specified?
  • Are expected failure modes stated?

Step 3: Theory Audit

Check:

  • Is there a theorem, derivation, proof sketch, identifiability argument, counterexample, or explicitly labeled heuristic theory?
  • Are assumptions stated?
  • Are theoretical predictions linked to experiments?
  • Are limitations clear?

Step 4: Experiment and Comparison Audit

Check:

  • Do experiments test the claims and theory predictions?
  • Are proposed method and baselines evaluated under comparable conditions?
  • Are failures, seeds, repetitions, folds, or resamples recorded?
  • Are theory-experiment disagreements discussed?

Step 5: Final Result Audit

Check:

  • Does each final claim trace back to formulation, theory, and evidence?
  • Are unsupported claims marked inconclusive?
  • Does the paper distinguish proven, derived, heuristic, and empirical results?
  • Are limitations honestly stated?

Step 6: Write Audit

Write progress/<TOPIC_ID>/step6_quality_audit.md with:

  • Status: PASS, WARN, or FAIL
  • Formulation check
  • Method check
  • Theory check
  • Experiment check
  • Comparison check
  • Blocking issues
  • Non-blocking warnings
  • Recommended fixes

Read the full file on GitHub · 105 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. 6d ago First seen · 105 lines · 37 tokens per session scan A 150c959ec7ad

Subscribe to this mod's changes

stat-quality-auditor is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,344 stars, last pushed 18d ago), licensed MIT. It adds 37 tokens to every session and 533 once invoked, about $0.0002 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.