growth-ab-test

growth-ab-test is a command for Claude Code from christopherlouet/claude-base. It costs 0 tokens per session (449 once invoked), scanned A, original, MIT.

An A/B testing command for planning and evaluating an experiment that compares two or more versions of something. It covers hypotheses, sample size, traffic allocation, and statistical results.

In plain words
What is it for?
It helps create a test plan, define primary and safety metrics, calculate duration and sample size, prepare variants, check launch readiness, and interpret results.
Why use it?
It helps teams decide whether a change genuinely improved a chosen metric instead of relying on random fluctuations or impressions.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit It helps create a test plan, define primary and safety metrics, calculate duration and sample size, prepare variants, check launch readiness, and interpret results.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/christopherlouet/claude-base/growth-ab-test
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.

Clone the repo
git clone --depth 1 https://github.com/christopherlouet/claude-base

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 growth-ab-test

README.md
[![agentmods](https://agentmods.dev/badge/commands/christopherlouet/claude-base/growth-ab-test.svg)](https://agentmods.dev/commands/christopherlouet/claude-base/growth-ab-test)
Your own site
<a href="https://agentmods.dev/commands/christopherlouet/claude-base/growth-ab-test"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/growth-ab-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00449
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 4d ago against content hash 2954dd418cdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

growth-ab-test 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.

.claude/commands/growth/growth-ab-test.md · 57 lines

What it actually says

GROWTH-AB-TEST Agent

Plan and analyze an A/B test.

Context

$ARGUMENTS

Objective

Define the hypothesis, calculate sample size, configure the test, and analyze the results with statistical rigor.

Workflow

  • Define the hypothesis (If [change], then [metric] [changes] by [X%], because [reason])
  • Identify the metrics (primary, secondary, guardrails)
  • Calculate sample size and duration (95% significance, 80% power)
  • Design the test (type, variants, traffic allocation)
  • Implement (feature flags, tracking)
  • Verify the pre-launch checklist
  • Analyze the results (p-value, confidence interval)
  • Document the learnings and decide

Expected output

Test plan

  • Hypothesis, primary metric, duration, sample, allocation
  • Description of variants
  • Success criteria

Results

Metric Control Treatment Lift p-value Significant

Decision and learnings

Agent When to use it
/growth:growth-analytics Define the metrics
/growth:growth-landing Optimize the landing pages
/growth:growth-cro Analyze the impact on the funnel

See also

For deeper A/B-test methodology (hypothesis templates, sample-size calculators, segmentation playbooks), pair this with coreyhaines31/marketingskills (ab-testing sub-skill) — install per docs/recipes/recommended-vendor-skills.md §"Corey Haines — coreyhaines31/marketingskills". Use the vendor for the deep execution layer; keep this command for the foundation workflow orchestration.


IMPORTANT: Never stop a test prematurely based on partial results.

YOU MUST reach the calculated sample size before concluding.

NEVER test several changes at once without a multivariate design.

Think hard about what you will do with the results before launching the test.

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 · 57 lines · 0 tokens per session scan A 2954dd418cdc

Subscribe to this mod's changes

growth-ab-test is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 449 tokens. 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 2026-09-03.