ab-testing

ab-testing is a skill for Claude Code, Codex from sendx/email-skills. It costs 18 tokens per session (1,006 once invoked), scanned A, original, MIT.

A skill for running controlled email experiments, called A/B tests, where different versions of one campaign element are compared. It is designed for SendX campaigns.

In plain words
What is it for?
Use it to compare subject lines, send times, sender names, content length, or call-to-action placement and interpret the results.
Why use it?
It helps distinguish real improvements in opens, clicks, or conversions from random variation in the results.

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

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/sendx/email-skills/ab-testing.svg)](https://agentmods.dev/skills/sendx/email-skills/ab-testing)
Your own site
<a href="https://agentmods.dev/skills/sendx/email-skills/ab-testing"><img src="https://agentmods.dev/badge/skills/sendx/email-skills/ab-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 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 $0.00018 $0.01006
Opus 5 $0.00009 $0.00503
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00101

Measured 3d ago against content hash 4fbea14b5196, 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 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.

skills/ab-testing/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A/B Testing for Email Campaigns

Your Setup — Fill These In for Better Results

This skill gives generic advice by default. Fill in your details below and it will calculate the right sample sizes and test durations for your list.

  • List size: [e.g., 20,000]
  • Current open rate: [e.g., 22%]
  • Current click rate: [e.g., 3%]
  • Sending frequency: [e.g., weekly]

What you do

You design and execute controlled experiments within SendX campaigns to compare how different email elements affect performance. You test one variable at a time, interpret results accurately, and use findings to improve future campaigns. You know when a test result is statistically meaningful versus random noise.

When to activate

Run A/B tests when you want to improve a specific metric (open rate, click rate, conversion) and have enough list size to see meaningful differences. Use A/B tests to inform decisions about subject lines, send times, sender names, content length, or call-to-action placement. Run tests on your highest-engagement segments first to see results faster.

Your expertise

You understand the mechanics of SendX A/B campaigns: multiple subject line variants, configurable test percentages to determine what portion of your audience sees the test, wait duration before the system automatically picks a winner, and automatic winner selection that sends the winning variant to the remaining audience. You know how to read campaign analytics to compare open rates, click rates, and click heatmaps between variants.

You also know about A/B Split nodes in SendX Visual Workflow Builder, which test entire customer journeys, not just subject lines. You recommend using the Bot Detection add-on when you test, so fake engagement from bots does not skew your results.

How to respond

When someone wants to run a test:

  1. Ask what they want to improve. Focus their test on one metric at a time. If they want to test multiple things, tell them to run separate tests over the next few months.

Read the full file on GitHub · 62 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 · 62 lines · 18 tokens per session scan A 4fbea14b5196

Subscribe to this mod's changes

ab-testing is a skill published in the GitHub repository sendx/email-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,006 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.

Related

Other skills, from other repositories

email-marketing-bible

Data-backed email marketing skill for AI agents. Use when building or running email automation, driving an ESP from an agent (MCP/connectors), diagnosing deliverability, writing or de-slopping email copy, designing emails, choosing a platform, or pulling benchmarks. Covers AI email automation, flows, deliverability…

CosmoBlk/email-marketing-bible · 93 tokens

upgrading-golang

Upgrades Go version across the entire Chainloop codebase including source files, Docker images, CI/CD workflows, and documentation. Use when the user mentions upgrading Go, golang version, or updating Go compiler version.

chainloop-dev/chainloop · 48 tokens

custom-builtin-functions

Create a custom builtin function to be used in the Rego policy engine.

chainloop-dev/chainloop · 19 tokens

catalyst-center-readonly

Query Cisco Catalyst Center read-only — device inventory, site hierarchy, wireless, assurance health, compliance, software images, events. All 514 read-only API operations reachable through 8 grouped dispatchers. Use when asked what Catalyst Center manages, where a device sits, what its health or compliance state is…

automateyournetwork/netclaw · 78 tokens

playwright-best-practices

Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…

currents-dev/playwright-best-practices-skill · 214 tokens

biome

Repository guidance for using Biome as the formatter, linter, and code quality tool within the hr-skills monorepo.

tuanductran/hr-skills · 29 tokens