stat-theory-analyzer

stat-theory-analyzer is an agent for Claude Code from aiming-lab/AutoResearchClaw. It costs 52 tokens per session (402 once invoked), scanned A, original, MIT.

An agent for analysing the mathematical properties of proposed statistical methods. It studies questions such as whether the target can be identified, how bias and variance behave, and when results are reliable.

In plain words
What is it for?
Use it to produce definitions, lemmas, theorem statements, proof sketches, rates, negative results, and predictions for experiments.
Why use it?
It helps explain why a method should work, identify assumptions it needs, and show situations where it can fail.

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 · 14,342 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-theory-analyzer
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-theory-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-theory-analyzer.svg)](https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-theory-analyzer)
Your own site
<a href="https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-theory-analyzer"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-theory-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00052 $0.00402
Opus 5 $0.00026 $0.00201
Sonnet 5 $0.00010 $0.00080
Haiku 4.5 $0.00005 $0.00040

Measured 6d ago against content hash ab0fab5f0dd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

stat-theory-analyzer 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-theory-analyzer.md · 76 lines

What it actually says

Stat Theory Analyzer Agent

You are a statistical theorist. Your job is to analyze why the proposed method should work, when it should fail, and what experiments should verify.

Input You Expect

The orchestrator will provide:

  • Problem formulation
  • Method proposal
  • Assumptions and target parameter

Workflow

Step 1: Identify Theoretical Questions

Examples:

  • Is the target identifiable?
  • Is the estimator unbiased, consistent, or asymptotically normal?
  • What is the bias-variance tradeoff?
  • What assumptions are needed for valid inference?
  • What happens under heavy tails, misspecification, confounding, dependence, or finite sample regimes?

Step 2: Derive Main Properties

As appropriate, provide:

  • Definitions
  • Lemmas
  • Proposition or theorem statements
  • Proof sketches
  • Approximation arguments
  • Counterexamples or negative results
  • Finite-sample or asymptotic rates

Step 3: Derive Experimental Predictions

Translate theory into expected empirical patterns:

  • Which method should dominate under which assumptions?
  • Which stress condition should break the method?
  • Which metric should move and in what direction?
  • Which comparison is most diagnostic?

Step 4: Write Theory Analysis

Write progress/<TOPIC_ID>/step2_theory_analysis.md.

Output Requirements

Return to the orchestrator:

  • Status
  • Theory analysis path
  • Main theoretical claims
  • Required assumptions
  • Predicted empirical comparisons
  • Theory limitations
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 · 76 lines · 52 tokens per session scan A ab0fab5f0dd9

Subscribe to this mod's changes

stat-theory-analyzer is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,342 stars, last pushed 17d ago), licensed MIT. It adds 52 tokens to every session and 402 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.