aso-ab-testing

aso-ab-testing is an agent for Claude Code from FelixGraeber/claude-aso-audit-skill. It costs 33 tokens per session (313 once invoked), scanned A, original, MIT.

An app-store experiment specialist for testing different versions of an app listing. A/B testing means comparing versions with real users to see which performs better; iOS PPO and Android Store Listing Experiments are the platform systems used for these tests.

In plain words
What is it for?
Use it to choose listing elements to test, create hypotheses for iOS or Android, assess experimentation maturity, and plan tests in sequence.
Why use it?
It turns weaknesses found in an app-store listing review into ranked test ideas and checks whether the listing is ready for experimentation.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-aso plugin — 7 skills, 12 agents shipped together

Good fit Use it to choose listing elements to test, create hypotheses for iOS or Android, assess experimentation maturity, and plan tests in sequence.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felixgraeber/claude-aso-audit-skill/aso-ab-testing
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/FelixGraeber/claude-aso-audit-skill

Made for: Claude Code.

Or install claude-aso, the plugin that ships this one along with the rest of its 7 skills, 12 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 aso-ab-testing

README.md
[![agentmods](https://agentmods.dev/badge/agents/felixgraeber/claude-aso-audit-skill/aso-ab-testing/github.svg)](https://agentmods.dev/agents/felixgraeber/claude-aso-audit-skill/aso-ab-testing)
Your own site
<a href="https://agentmods.dev/agents/felixgraeber/claude-aso-audit-skill/aso-ab-testing"><img src="https://agentmods.dev/badge/agents/felixgraeber/claude-aso-audit-skill/aso-ab-testing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aso-ab-testing

Your own site · 80×15
<a href="https://agentmods.dev/agents/felixgraeber/claude-aso-audit-skill/aso-ab-testing"><img src="https://agentmods.dev/badge/agents/felixgraeber/claude-aso-audit-skill/aso-ab-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 313 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 $0.00033 $0.00313
Opus 5 $0.00016 $0.00156
Sonnet 5 $0.00007 $0.00063
Haiku 4.5 $0.00003 $0.00031

Measured 10d ago against content hash 638a642321fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

aso-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 10d 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.

agents/aso-ab-testing.md · 45 lines

What it actually says

A/B Testing Agent

Role

Assess experimentation readiness and generate test hypotheses from audit findings.

Input

Listing JSON, audit findings from other agents (if available), platform identifier.

Responsibilities

  1. Assess current experimentation status (any active tests?)
  2. Identify highest-impact testable elements
  3. Generate 2-3 test hypotheses ranked by expected impact
  4. Platform-specific experiment design
  5. Score experimentation maturity (0-100)

Platform Capabilities

iOS PPO

  • Testable: icon, screenshots, app preview video
  • NOT testable: title, subtitle, keywords, description
  • Max 3 treatments + original
  • 1 active test at a time

Android Experiments

  • Testable: icon, feature graphic, screenshots, short desc, full desc, video
  • Up to 5 localized + 1 main simultaneously
  • Configurable traffic split

Hypothesis Priority

  1. Screenshots (highest conversion impact)
  2. App icon (affects all impression types)
  3. Short description / feature graphic (Android)
  4. Preview video (presence/absence)

Output

Return JSON with score, recommended tests (hypothesis, element, expected impact), and a sequential test roadmap.

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. 10d ago First seen · 45 lines · 33 tokens per session scan A 638a642321fc

Subscribe to this mod's changes

aso-ab-testing is an agent published in the GitHub repository FelixGraeber/claude-aso-audit-skill (4 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 313 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 2026-08-31.