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 wdavidturner/product-skills --skill trustworthy-experimentsgit clone --depth 1 https://github.com/wdavidturner/product-skillsWrote 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/wdavidturner/product-skills/trustworthy-experiments)<a href="https://agentmods.dev/skills/wdavidturner/product-skills/trustworthy-experiments"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/trustworthy-experiments/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/wdavidturner/product-skills/trustworthy-experiments"><img src="https://agentmods.dev/badge/skills/wdavidturner/product-skills/trustworthy-experiments.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 | $0.00071 | $0.01339 |
| Opus 5 | $0.00036 | $0.00669 |
| Sonnet 5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
trustworthy-experiments 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trustworthy Experiments
What It Is
Trustworthy Experiments is a framework for running controlled experiments (A/B tests) that produce reliable, actionable results. The core insight: most experiments fail, and many "successful" results are actually false positives.
The key shift: Move from "Did the experiment show a positive result?" to "Can I trust this result enough to act on it?"
Ronny Kohavi, who built experimentation platforms at Microsoft, Amazon, and Airbnb, found that:
- 66-92% of experiments fail to improve the target metric
- 8% of experiments have invalid results due to sample ratio mismatch alone
- When the base success rate is 8%, a P-value of 0.05 still means 26% false positive risk
This framework helps you avoid the common traps that make experiment results untrustworthy.
Response Posture
- Apply the framework directly to the user's experiment.
- Never mention the repository, skills, SKILL.md, patterns, or references.
- Do not run tools or read files; answer from the framework.
- Avoid process/meta commentary; respond as an experimentation lead.
When to Use It
Use Trustworthy Experiments when you need to:
- Design an A/B test that will produce valid, actionable results
- Determine sample size and runtime for statistical power
- Validate experiment results before making ship/no-ship decisions
- Build an experimentation culture at your company
- Choose metrics (OEC) that balance short-term gains with long-term value
- Diagnose why results look suspicious (Twyman's Law)
- Speed up experimentation without sacrificing validity
When Not to Use It
Don't use controlled experiments when:
- You don't have enough users — Need tens of thousands minimum; 200,000+ for mature experimentation
- The decision is one-time — Can't A/B test mergers, acquisitions, or one-off events
- There's no real user choice — Employer-mandated software offers no switching insight
- You need immediate decisions — Experiments need time to reach statistical power
- The metric can't be measured — No experiment without observable outcomes
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- patterns/_template.md 460 B
- patterns/big-redesigns-fail.md 2.0 KB
- patterns/external-validity.md 2.1 KB
- patterns/flat-is-not-ship.md 1.9 KB
- patterns/guardrail-metrics.md 1.8 KB
- patterns/institutional-memory.md 2.0 KB
- patterns/multiple-comparisons.md 2.4 KB
- patterns/novelty-effects.md 1.7 KB
- patterns/peeking-at-results.md 1.7 KB
- patterns/sample-ratio-mismatch.md 1.7 KB
- patterns/survivorship-bias.md 2.0 KB
- patterns/twymans-law.md 2.0 KB
- patterns/underpowered-tests.md 1.9 KB
- patterns/variance-reduction.md 2.4 KB
- patterns/wrong-success-metric.md 1.9 KB
- references/experiment-plan-template.md 3.2 KB
- references/trustworthy-experiments-playbook.md 12 KB
- scripts/sample_size.py 4.1 KB runs code
- scripts/srm_check.py 2.9 KB runs code
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.
- 11d ago First seen · 117 lines · 71 tokens per session scan A 04271890acf2
trustworthy-experiments is a skill published in the GitHub repository wdavidturner/product-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 71 tokens to every session and 1,339 once invoked, about $0.0004 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…
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…