arnesto: Skill for Claude Code

.agents/skills/trustworthy-experiments/SKILL.md

trustworthy-experiments is a skill for Claude Code, Codex from saski/arnesto. It costs 71 tokens per session (540 once invoked), scanned A, a copy of trustworthy-experiments, Unlicense.

A framework for designing and interpreting controlled experiments, also called A/B tests, so their results can be trusted.

In plain words
What is it for?
Use it to plan experiments, check statistical significance, detect sample-ratio problems, and define safety limits for changes.
Why use it?
It helps detect false positives and setup problems before you act on an apparently successful experiment.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is saski/arnesto's own configuration. It tells Claude Code and Codex how to work on arnesto itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything arnesto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saski/arnesto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saski/arnesto/main/.agents/skills/trustworthy-experiments/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/saski/arnesto

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 trustworthy-experiments

README.md
[![agentmods](https://agentmods.dev/badge/skills/saski/arnesto/trustworthy-experiments.svg)](https://agentmods.dev/skills/saski/arnesto/trustworthy-experiments)
Your own site
<a href="https://agentmods.dev/skills/saski/arnesto/trustworthy-experiments"><img src="https://agentmods.dev/badge/skills/saski/arnesto/trustworthy-experiments.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 540 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 100% copy Near-identical to another mod 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 $0.00071 $0.00540
Opus 5 $0.00036 $0.00270
Sonnet 5 $0.00014 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured 3d ago against content hash 2dc69fa061d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

Origin

This is a copy

100% identical to trustworthy-experiments — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/trustworthy-experiments/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Context

This skill implements a proven product management framework. The approach combines best practices from industry leaders and is designed for practical application in day-to-day PM work.

Input Requirements

  • Context about your product, feature, or problem
  • Relevant data, research, or constraints (recommended but optional)
  • Clear articulation of what you're trying to achieve

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

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
  • The decision is one-time — Can't A/B test mergers or acquisitions
  • There's no real user choice — Employer-mandated software
  • You need immediate decisions — Experiments need time
  • The metric can't be measured — No experiment without observable outcomes

Read the full file on GitHub · 56 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 · 56 lines · 71 tokens per session scan A 2dc69fa061d7

Subscribe to this mod's changes

trustworthy-experiments is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed today), licensed Unlicense. It adds 71 tokens to every session and 540 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to trustworthy-experiments, differing in 0 lines, and is treated as a copy.