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 uthumany/uthy-legacy-os --skill ab-test-readergit clone --depth 1 https://github.com/uthumany/uthy-legacy-osWrote 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/uthumany/uthy-legacy-os/ab-test-reader)<a href="https://agentmods.dev/skills/uthumany/uthy-legacy-os/ab-test-reader"><img src="https://agentmods.dev/badge/skills/uthumany/uthy-legacy-os/ab-test-reader/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/uthumany/uthy-legacy-os/ab-test-reader"><img src="https://agentmods.dev/badge/skills/uthumany/uthy-legacy-os/ab-test-reader.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 | $0.00027 | $0.00924 |
| Opus 5 | $0.00014 | $0.00462 |
| Sonnet 5 | $0.00005 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
ab-test-reader 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 9d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A/B Test Reader
Overview
A/B tests produce numbers — but not every number is meaningful. This skill helps you read A/B test results critically, understand statistical concepts in plain language, and avoid common interpretation mistakes.
When to Use
- An A/B test has concluded and you need to interpret the results
- You're reviewing a test designed by someone else
- You want to understand why a test result might be misleading
- Don't use for: designing the test (use experiment-design skill), non-experimental data comparisons
Instructions
1. Check the Basics
Before trusting the results, verify:
- Random assignment: Was each user truly randomly assigned?
- Sample size: Was the sample large enough to detect your expected effect?
- Duration: Did it run at least 1-2 weeks (to capture full weekly cycles)?
- No peeking: Was the test analyzed only at the END? (peeking inflates false positive rate)
- No other changes: Were there no simultaneous changes that could confound results?
2. Understand the Numbers
Statistical significance (p-value):
- p < 0.05 = 95% chance the effect is real (5% chance it's random noise)
- Not a measure of effect size — a tiny effect can be significant with a large sample
- Don't compare p-values — a test with p=0.001 is not "more significant" than p=0.04
Effect size:
- Absolute lift: Treatment - Control (e.g., 12% - 10% = +2%)
- Relative lift: (Treatment - Control) / Control (e.g., +20% relative)
- Report both — absolute is more honest
Confidence interval:
- The range where the true effect likely lives
- CI = [2%, 8%] means the true effect is likely between +2% and +8%
- If CI crosses zero ([-1%, 5%]), the result is NOT significant
3. Look for Issues
- Multiple metrics: Testing 20 metrics and reporting the one that's significant = p-hacking
- Post-hoc segmentation: Slicing the data 50 ways until something is significant
- Novelty effect: Early positive effect that fades (common with UI changes)
- Primacy effect: Early negative effect that recovers (common with major redesigns)
- Sample ratio mismatch: 50/50 split is actually 48/52 — something's wrong
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.
- 9d ago First seen · 87 lines · 27 tokens per session scan A 58eb6bbd2681
ab-test-reader is a skill published in the GitHub repository uthumany/uthy-legacy-os (5 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 924 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.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…