experiment-brief

experiment-brief is a skill for Claude Code from ai-analyst-lab/ai-analyst-plugin. It costs 91 tokens per session (2,572 once invoked), scanned A, original, MIT.

A structured planning brief for a proposed experiment, including its hypothesis, main success measure, safety measures, thresholds, and estimated duration. An A/B test compares two versions to see which performs better.

In plain words
What is it for?
Use it when someone wants to test a product or process change, including requests for an A/B test, so the hypothesis, metrics, success criteria, and feasibility are defined first.
Why use it?
It forces the important decisions to be made before the test is designed or run. This reduces vague goals, missing guardrails, and unclear rules for deciding what to do afterward.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the ai-analyst-plus plugin — 44 skills, 1 command, 13 agents shipped together

Good fit Use it when someone wants to test a product or process change, including requests for an A/B test, so the hypothesis, metrics, success criteria, and feasibility are defined first.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai-analyst-lab/ai-analyst-plugin/experiment-brief
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.

Any agent
npx skills add ai-analyst-lab/ai-analyst-plugin --skill experiment-brief
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plugin

Made for: Claude Code.

Or install ai-analyst-plus, the plugin that ships this one along with the rest of its 44 skills, 1 command, 13 agents.

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 experiment-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/experiment-brief/github.svg)](https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/experiment-brief)
Your own site
<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/experiment-brief"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/experiment-brief/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.

agentmods 80×15 button for experiment-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/experiment-brief"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/experiment-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,572 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 59
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 95
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 106
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 106
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 207
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 5.1 $0.00091 $0.02572
Opus 5 $0.00046 $0.01286
Sonnet 5 $0.00018 $0.00514
Haiku 4.5 $0.00009 $0.00257

Measured 8d ago against content hash 74ff2e74ac6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

experiment-brief 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 8d 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.

ai-analyst-plus/skills/experiment-brief/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Experiment Brief

Purpose

Auto-generate a structured experiment brief when a user expresses intent to test something. This is the "think before you design" safety net — ensuring every experiment starts with a clear hypothesis, north star metric, guardrail metrics, success criteria, and duration estimate before the Experiment Designer agent runs.

When to Use

Apply this skill when:

  1. The user says "I want to test..." or "Let's experiment with..." or "Should we A/B test..." or any variant expressing intent to run an experiment
  2. Before invoking the Experiment Designer agent — the brief is a prerequisite input
  3. When an experiment request is vague — the user wants to test something but hasn't specified metrics, duration, or success criteria

This skill auto-fires on experiment intent detection. Do NOT wait to be asked.

Critical Requirements

The brief must be COMPLETE and ACTIONABLE:

  • No "TBD" placeholders — all decisions are made in the brief
  • No "Would you like me to..." deferral — do the work now
  • No missing thresholds — every guardrail has a number
  • No ambiguous success criteria — ship/kill/iterate conditions are specific
  • Always includes a VIABLE/MARGINAL/NOT_VIABLE feasibility flag

If the user provides baseline values, VALIDATE them by querying the data first. Correct misstatements with actual numbers before using them in the brief.

Instructions

What Is an Experiment Brief?

An experiment brief is a one-page document that captures the essential decisions BEFORE any statistical design work begins. It answers: What are we testing? Why? How will we know if it worked? What must we not break?

EXPERIMENT BRIEF
━━━━━━━━━━━━━━━━
WHAT:       What change are we testing?
WHY:        What business outcome do we expect?
HYPOTHESIS: We believe [change] will [impact metric] because [reason]
NORTH STAR: The ONE metric we're trying to move
GUARDRAILS: Metrics that must NOT degrade
SUCCESS:    What result would make us ship?
DURATION:   Rough estimate of how long we'd need to run

Read the full file on GitHub · 208 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. 8d ago First seen · 208 lines · 91 tokens per session scan A 74ff2e74ac6c

Subscribe to this mod's changes

experiment-brief is a skill published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 12d ago), licensed MIT. It adds 91 tokens to every session and 2,572 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens