experiment-analyzer

experiment-analyzer is an agent for coding agents from ai-analyst-lab/ai-analyst-plugin. It costs 39 tokens per session (3,251 once invoked), scanned A, original, MIT.

An agent that analyzes an experiment from its data through its final recommendation. An experiment compares groups to measure whether a change caused a different outcome.

In plain words
What is it for?
Use it to evaluate experiment data, measure treatment effects, inspect user segments and guardrails, and recommend whether to launch, stop, or improve a change.
Why use it?
It checks more than whether a result is statistically significant, including data validity, uneven assignment, subgroup reversals, duration, business impact, and safety metrics.

Agent

Part of the ai-analyst-plus plugin — 44 skills, 1 command, 13 agents shipped together

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/ai-analyst-lab/ai-analyst-plugin/experiment-analyzer
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plugin

Or install ai-analyst-plus, the plugin that ships this one along with the rest of its 44 skills, 1 command, 13 agents.

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-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/experiment-analyzer.svg)](https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/experiment-analyzer)
Your own site
<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/experiment-analyzer"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/experiment-analyzer.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 3,251 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 $0.00039 $0.03251
Opus 5 $0.00019 $0.01625
Sonnet 5 $0.00008 $0.00650
Haiku 4.5 $0.00004 $0.00325

Measured 4d ago against content hash 8b9bfcc87696, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

experiment-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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

ai-analyst-plus/agents/experiment-analyzer.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Experiment Analyzer

Purpose

Conduct a complete experiment analysis following the 8-question framework used by senior data scientists at top tech companies. Takes raw experiment data and produces a thorough, nuanced analysis that goes far beyond "significant or not" — checking validity, quantifying effects, detecting segment-level reversals (Simpson's paradox), evaluating duration adequacy, projecting business impact, and delivering a conditional recommendation.

Inputs

  • {{EXPERIMENT_DATA}}: Path to the experiment dataset (CSV, parquet, or database table). Must contain at minimum: user identifier, treatment assignment column, and outcome metric(s).
  • {{PRIMARY_METRIC}}: The north star metric for this experiment (e.g., streams_post_14d, conversion, revenue_per_user). Must match a column name or be derivable from columns in the dataset.
  • {{GUARDRAIL_METRICS}}: Comma-separated list of guardrail metrics to check (e.g., churned, support_tickets). Apply Guardrails Awareness skill if not specified.
  • {{TREATMENT_COLUMN}}: (optional) Column name indicating group assignment. If not provided, auto-detect from column names (variant, group, treatment, arm, experiment_group, bucket).
  • {{SEGMENT_COLUMNS}}: (optional) Comma-separated list of columns to use for segment analysis. If not provided, auto-detect all categorical columns with 2-20 unique values.

Query Logging

After every SQL query you execute (via MCP tool or inline), log it by running this Bash command:

python3 scripts/log_query.py \
    --dataset {{DATASET_NAME}} --date {{DATE}} \
    --agent experiment-analyzer --step 0 \
    --purpose "Brief description of why this query ran" \
    --sql "THE SQL QUERY TEXT" \
    --dialect {{DIALECT}} --connection {{CONNECTION_TYPE}} \
    --tables TABLE1 TABLE2 \
    --result "Brief result summary" --rows N

Log failed queries too (add --status error --error "message").

The 8-Question Framework

This agent answers the 8 questions every rigorous experiment analysis must address:

Read the full file on GitHub · 320 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 First seen · 320 lines · 39 tokens per session scan A 8b9bfcc87696

Subscribe to this mod's changes

experiment-analyzer is an agent published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 3,251 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.