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.
npx skills add coleschaffer/copywritingskills-rmbc --skill ab-test-plangit clone --depth 1 https://github.com/coleschaffer/copywritingskills-rmbcWrote 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.
[](https://agentmods.dev/skills/coleschaffer/copywritingskills-rmbc/ab-test-plan)<a href="https://agentmods.dev/skills/coleschaffer/copywritingskills-rmbc/ab-test-plan"><img src="https://agentmods.dev/badge/skills/coleschaffer/copywritingskills-rmbc/ab-test-plan/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.
<a href="https://agentmods.dev/skills/coleschaffer/copywritingskills-rmbc/ab-test-plan"><img src="https://agentmods.dev/badge/skills/coleschaffer/copywritingskills-rmbc/ab-test-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.01987 |
| Opus 5 | $0.00019 | $0.00993 |
| Sonnet 5 | $0.00008 | $0.00397 |
| Haiku 4.5 | $0.00004 | $0.00199 |
Grade A, and why
ab-test-plan 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ab-test-plan
Purpose
Generate structured A/B test plans for DTC funnels. Testing is how you turn opinions into revenue data. Most teams waste tests by changing too many variables, running too short, or measuring the wrong metric. This skill produces a single, clean test plan with a falsifiable hypothesis, defined control and variant, primary metric, sample size estimate, expected duration, and success criteria. Every test plan connects back to RMBC — you're testing Research assumptions, Mechanism angles, Brief strategies, or Copy execution.
Inputs
| Input | Required | Description |
|---|---|---|
page_type |
Yes | What you're testing: landing_page, order_form, upsell, email, ad, checkout |
current_metric |
Yes | Baseline performance: conversion rate, CTR, AOV, or revenue per visitor |
hypothesis |
Yes | What you believe will improve performance and why |
traffic_volume |
Yes | Daily unique visitors or impressions to the test page |
test_element |
Yes | One of: headline, price, offer, layout, copy_length, mechanism, cta, guarantee, social_proof |
Execution Protocol
Step 1 — Load Framework Context
Read rmbc-context/SKILL.md to load RMBC framework definitions. A/B testing validates RMBC decisions with data — Research assumptions get tested through audience-facing copy, Mechanism strength gets tested through conversion lift, Brief strategy gets tested through engagement, Copy execution gets tested through click and purchase behavior.
Step 2 — Classify the Test Type
| Test Type | What Changes | Typical Lift | Risk Level |
|---|---|---|---|
| Headline | Lead/hook copy only | 5-30% | Low — copy swap, no structural change |
| Price | Price point or framing | 10-50% | Medium — affects AOV and refund rate |
| Offer | What's included in the deal | 15-60% | Medium — may affect fulfillment |
| Layout | Page structure, element order | 5-20% | Low-Medium — design change only |
| Copy Length | Long vs short form | 10-40% | Low — same offer, different depth |
| Mechanism | Which "why it works" angle | 10-35% | Low — copy change, different angle |
| CTA | Button text, placement, urgency | 5-15% | Low — smallest change, quickest test |
| Guarantee | Risk reversal type or duration | 5-25% | Low-Medium — may affect refund rate |
| Social Proof | Testimonials, numbers, authority | 5-20% | Low — additive element |
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.
- 12d ago First seen · 184 lines · 39 tokens per session scan A b17d246a8d43
ab-test-plan is a skill published in the GitHub repository coleschaffer/copywritingskills-rmbc (30 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,987 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…