growth-experiment

growth-experiment is a command for coding agents from brainbytes-dev/everything-claude-marketing. It costs 22 tokens per session (1,952 once invoked), scanned A, original, MIT.

A command for planning a growth experiment, such as testing a feature, price, onboarding flow, or marketing campaign. ICE is a way to prioritize ideas by estimated impact, confidence, and ease.

In plain words
What is it for?
Use it to create hypotheses, prioritize experiments, choose primary and safety metrics, define success criteria, and plan timelines.
Why use it?
It turns a broad growth idea into a test with defined measurements, success rules, sample-size guidance, and decision dates.

Command

Part of the everything-claude-marketing plugin — 15 skills, 22 commands, 18 agents, 2 hooks 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 commands/brainbytes-dev/everything-claude-marketing/growth-experiment
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing

Or install everything-claude-marketing, the plugin that ships this one along with the rest of its 15 skills, 22 commands, 18 agents, 2 hooks.

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-experiment

README.md
[![agentmods](https://agentmods.dev/badge/commands/brainbytes-dev/everything-claude-marketing/growth-experiment.svg)](https://agentmods.dev/commands/brainbytes-dev/everything-claude-marketing/growth-experiment)
Your own site
<a href="https://agentmods.dev/commands/brainbytes-dev/everything-claude-marketing/growth-experiment"><img src="https://agentmods.dev/badge/commands/brainbytes-dev/everything-claude-marketing/growth-experiment.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,952 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 $0.00022 $0.01952
Opus 5 $0.00011 $0.00976
Sonnet 5 $0.00004 $0.00390
Haiku 4.5 $0.00002 $0.00195

Measured 3d ago against content hash 1f5ac69cb274, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

growth-experiment 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 3d 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.

commands/growth-experiment.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/growth-experiment

Design a structured growth experiment with a clear hypothesis, ICE prioritization score, defined metrics, and success criteria — ready to run and measure.

What This Command Does

This command takes a growth idea and transforms it into a rigorous experiment framework. Instead of just launching features and hoping for the best, it structures your test with a falsifiable hypothesis, defines the minimum sample size for statistical significance, sets primary and guardrail metrics, establishes clear success criteria before the experiment begins, and creates a timeline with decision points. The output follows the scientific method applied to growth — so you learn something valuable whether the experiment succeeds or fails.

When to Use

  • Testing a new feature's impact on activation, retention, or revenue
  • Evaluating a change to onboarding flow, pricing, or packaging
  • Running A/B tests on landing pages, email sequences, or ad creative
  • Validating a referral, loyalty, or viral growth mechanic
  • Testing a new acquisition channel before committing significant budget
  • Experimenting with pricing models, trial lengths, or freemium limits
  • Prioritizing a backlog of growth ideas using a consistent framework
  • Building a culture of experimentation within your team

How It Works

  1. Captures the idea — Understands what you want to test and the business context behind it
  2. Formulates the hypothesis — Structures a falsifiable hypothesis with expected outcome and mechanism
  3. Scores with ICE — Rates the experiment on Impact, Confidence, and Ease to help you prioritize
  4. Defines metrics — Sets one primary metric, supporting metrics, and guardrail metrics that must not degrade
  5. Calculates sample size — Determines how many users or events you need for statistically significant results
  6. Sets success criteria — Defines what "winning" looks like before the experiment runs, eliminating post-hoc rationalization
  7. Plans execution — Outlines implementation steps, required resources, and timeline
  8. Creates the decision framework — Defines what happens if the experiment wins, loses, or is inconclusive

Read the full file on GitHub · 220 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. 3d ago First seen · 220 lines · 22 tokens per session scan A 1f5ac69cb274

Subscribe to this mod's changes

growth-experiment is a command published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,952 once invoked, about $0.0001 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 2026-08-31.