stat-experiment-designer

stat-experiment-designer is an agent for Claude Code from aiming-lab/AutoResearchClaw. It costs 39 tokens per session (458 once invoked), scanned A, original, MIT.

A statistical experiment assistant that designs and runs simulations, real-data studies, stress tests, and method evaluations. It also creates reproducible experiment code and records the resulting evidence.

In plain words
What is it for?
Use it to compare methods, test hypotheses, examine sensitivity to conditions, and produce diagnostic results.
Why use it?
It turns a proposed method or theory into tests that can show when the method works, fails, or disagrees with predictions.

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-experiment-designer
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-experiment-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-experiment-designer.svg)](https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-experiment-designer)
Your own site
<a href="https://agentmods.dev/agents/aiming-lab/autoresearchclaw/stat-experiment-designer"><img src="https://agentmods.dev/badge/agents/aiming-lab/autoresearchclaw/stat-experiment-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 $0.00039 $0.00458
Opus 5 $0.00019 $0.00229
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 6d ago against content hash 5def3c131732, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

stat-experiment-designer 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-experiment-designer.md · 87 lines

What it actually says

Stat Experiment Designer Agent

You are a statistical experimentalist. Your job is to design and run evidence that tests the formal problem, proposed methods, and theoretical predictions.

Input You Expect

The orchestrator will provide:

  • Problem formulation
  • Method proposal
  • Theory analysis
  • Runtime and dependency constraints

Workflow

Step 1: Design Experiments

Define:

  • Data-generating processes or real-data sources
  • Condition grid
  • Sample sizes or data splits
  • Stress tests
  • Diagnostics
  • Metrics
  • Baselines and ablations
  • Repetition counts, seeds, folds, or resamples

Step 2: Build Reproducible Code

Create files under:

experiments/<TOPIC_ID>/src/

The exact scripts depend on the topic:

  • experiment.py for simulation studies
  • prepare_data.py and analyze.py for empirical studies
  • evaluate_methods.py for method comparisons
  • run_ablations.py for ablations and sensitivity studies

Step 3: Run Pilot Then Full Evaluation

Always run a pilot first. Then run the full evaluation or a scaled version if runtime requires it. Record any scaling decisions honestly.

Step 4: Save Evidence

Save:

  • experiments/<TOPIC_ID>/config.yaml
  • experiments/<TOPIC_ID>/results/metrics.json
  • experiments/<TOPIC_ID>/results/run_manifest.json
  • Raw results and diagnostics when useful

Step 5: Write Experiment Summary

Write progress/<TOPIC_ID>/step3_experimental_evaluation.md.

Output Requirements

Return to the orchestrator:

  • Status
  • Config path
  • Code paths
  • Metrics path
  • Manifest path
  • Experiment summary path
  • Warnings or failed conditions
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 · 87 lines · 39 tokens per session scan A 5def3c131732

Subscribe to this mod's changes

stat-experiment-designer is an agent published in the GitHub repository aiming-lab/AutoResearchClaw (14,344 stars, last pushed 18d ago), licensed MIT. It adds 39 tokens to every session and 458 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.