ab-testing

ab-testing is a skill for Claude Code, Codex from ericrisco/rsc-harness. It costs 79 tokens per session (2,450 once invoked), scanned A, original, MIT.

A guide for designing and evaluating A/B tests, which compare two versions of something with different groups of users. It covers choosing a measurable hypothesis, deciding how much data is needed, and interpreting results.

In plain words
What is it for?
Use it to plan controlled product experiments, choose a main measurement, estimate the needed sample size, set safeguards, and assess statistical results.
Why use it?
It reduces the risk of treating random fluctuations as real improvements or changing an experiment's rules midway.

Skill for Claude CodeCodex

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 skills/ericrisco/rsc-harness/ab-testing
Any agent
npx skills add ericrisco/rsc-harness --skill ab-testing
Clone the repo
git clone --depth 1 https://github.com/ericrisco/rsc-harness

Made for: Claude Code, Codex.

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 ab-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/ericrisco/rsc-harness/ab-testing.svg)](https://agentmods.dev/skills/ericrisco/rsc-harness/ab-testing)
Your own site
<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/ab-testing"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/ab-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,450 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 $0.00079 $0.02450
Opus 5 $0.00039 $0.01225
Sonnet 5 $0.00016 $0.00490
Haiku 4.5 $0.00008 $0.00245

Measured 4d ago against content hash 9e283bf5c950, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ab-testing 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/ab-testing/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A/B testing — design and read a defensible experiment

An experiment without a pre-committed sample size and a single primary metric is not an experiment. It is a dashboard you stare at until it tells you what you wanted to hear. The discipline lives almost entirely before traffic ships: a falsifiable hypothesis, one primary metric, a sample size derived from the smallest effect worth detecting, and a stop rule you cannot renegotiate at 2pm on day four.

Pre-test checklist — every line true before any traffic

Each one is a place experiments die silently.

  • A falsifiable hypothesis — names the change, the direction, and the metric it moves.
  • Exactly ONE primary metric. More than one primary = multiple comparisons = inflated false positives.
  • Guardrail metrics — what you refuse to harm (latency, refunds, unsubscribes) even for a win.
  • The randomization unit = the analysis unit (usually the user). Mixing them is pseudoreplication.
  • An MDE — the smallest lift that would change a decision. Not "any difference."
  • A computed sample size and the duration it implies at your real daily eligible traffic.
  • A fixed stop rule — a date or an n you commit to before launch. No "we'll see how it looks."

Step 1 — Hypothesis and metrics

State a null you can reject. "The new checkout button changes purchase conversion" with H0: conversion equal across arms, H1: it differs. Vague aspirations ("improve the funnel") have no rejection region.

Pick one primary metric and freeze it. Why: every extra primary metric is another coin flip at α, so three "primary" metrics turn a 5% false-positive rate into roughly 14%. Demote the rest to secondary.

Randomize on the same unit you analyze on. If a user sees the variant on every visit, randomize by user, not by session — analyzing 50k sessions from 8k users treats correlated observations as independent and fabricates significance.

Bad:  "We think the redesign will improve engagement and revenue and retention."  (no null, 3 primaries, no number)
Good: "H0: 30-day purchase conversion is equal between control and the new one-click button.
       H1: it differs. Primary: purchase conversion. Guardrails: refund rate, p95 checkout latency.
       Randomize by user_id. MDE: +1.5pp absolute on a 12% baseline."

Read the full file on GitHub · 160 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 160 lines · 79 tokens per session scan A 9e283bf5c950

Subscribe to this mod's changes

ab-testing is a skill published in the GitHub repository ericrisco/rsc-harness (60 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 2,450 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

ab-testing-ecommerce

Run controlled experiments on product pages, checkout flows, and pricing to find what converts best using statistical significance testing.

finsilabs/awesome-ecommerce-skills · 26 tokens

A/B Test Designer

Design statistically valid A/B tests for marketing optimization.

jmsktm/claude-settings · 14 tokens

featurevisor

Author, query, and integrate Featurevisor — Git-based feature flags, A/B experiments, and remote config. Use whenever the user mentions Featurevisor, works in a project containing featurevisor.config.js, edits files under attributes/, segments/, features/, variables/, groups/, schemas/, targets/, sets/, or tests/…

featurevisor/featurevisor · 266 tokens

A/B Test Validation

Validating A/B test implementations including traffic splitting accuracy, statistical significance calculation, metric tracking, and experiment cleanup.

PramodDutta/qaskills · 27 tokens

research-collaborator

Use this skill whenever a researcher wants to test, validate, stress-test, or falsify a research idea or hypothesis — especially in AI/ML/deep learning. Trigger on phrases like "I have an idea," "would this work," "test this hypothesis," "sanity check my idea," "what's wrong with this idea," "review my results," "is…

saidwivedi/research-skills · 108 tokens

conversion-optimizer

!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults".

buiphucminhtam/forgewright · 62 tokens