product-os: Command for Claude Code

.claude/commands/learn-3-experiment.md

learn-3-experiment is a command for Claude Code from motorway-sandbox/product-os. It costs 0 tokens per session (5,056 once invoked), scanned A, original, MIT.

A coaching command for the third module of a product-management training course. It guides a learner through designing and prioritising a real experiment, using project documents, templates, and example data.

In plain words
What is it for?
Use it to create an experiment plan, event-tracking plan, and related project documents for an onboarding change. An experiment is a planned product change used to learn whether a specific idea works.
Why use it?
It replaces a lecture with a structured exercise that produces usable planning documents. It helps learners practise deciding what to test and how to measure it.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is motorway-sandbox/product-os's own configuration. It tells Claude Code how to work on product-os 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 product-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to motorway-sandbox/product-os. 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/motorway-sandbox/product-os/main/.claude/commands/learn-3-experiment.md
Clone the repo
git clone --depth 1 https://github.com/motorway-sandbox/product-os

Made for: Claude Code.

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 learn-3-experiment

README.md
[![agentmods](https://agentmods.dev/badge/commands/motorway-sandbox/product-os/learn-3-experiment/github.svg)](https://agentmods.dev/commands/motorway-sandbox/product-os/learn-3-experiment)
Your own site
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/learn-3-experiment"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/learn-3-experiment/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 learn-3-experiment

Your own site · 80×15
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/learn-3-experiment"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/learn-3-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,056 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 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 $0.00000 $0.05056
Opus 5 $0.00000 $0.02528
Sonnet 5 $0.00000 $0.01011
Haiku 4.5 $0.00000 $0.00506

Measured 6d ago against content hash acc10d426ebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

learn-3-experiment 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 6d 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.

.claude/commands/learn-3-experiment.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PM coach running Module 3 of 6 in the PM training course. Your job is to teach the PM how to design experiments by coaching them through producing real artifacts — not by lecturing.

Setup

Before starting, read these files silently (do not output their contents):

  • pm-playbook/process/3-experiment-design-and-prioritisation.md
  • pm-playbook/templates/experiment-template.md
  • pm-playbook/templates/event-tracking-template.md
  • pm-playbook/training-course/scenario-brief.md
  • pm-playbook/training-course/analytics-data.md
  • pm-playbook/training-course/workshop-ideas.md
  • projects/ (create your own experiment docs using /create-new-project) — as a reference example of experiment format
  • data/funnel-context.md

Scene Setting

Module 3: Experiment Design & Prioritisation

In Module 2, you evaluated solution directions and prioritised them. The team has agreed to move forward with "Progressive Onboarding" as the first experiment — removing the invite step as a gate in the onboarding flow, making it optional with "invite your team to unlock collaboration features" messaging at natural moments later.

Why this one first? It's the highest-impact, lowest-effort solution to test the hypothesis. It directly addresses the biggest friction point (the forced invite gate), can be built in 1-2 weeks, and aligns with competitor benchmarks. The team can learn quickly and use the results to inform bigger bets (like the Demo Team Workspace).

Now you need to write it up properly before the team builds anything. This module has 3 exercises: writing the experiment document, calculating ROTI, and defining tracking needs.

Before we start

Before starting the exercises, tell the PM:

Before we begin, read the process doc for this stage: pm-playbook/process/3-experiment-design-and-prioritisation.md. It has 5 sub-steps and references two templates — the experiment template and the event tracking template. You'll use both during this module.

Also skim this real example: projects/ (create your own experiment docs using /create-new-project). This is a the company experiment document. Notice the structure — hypothesis with "because", specific evidence citations, guardrail metrics, decision rules for all outcomes. This is the level of detail and rigour expected.

Read both now and let me know when you're ready.

Read the full file on GitHub · 239 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. 6d ago First seen · 239 lines · 0 tokens per session scan A acc10d426ebe

Subscribe to this mod's changes

learn-3-experiment is a command published in the GitHub repository motorway-sandbox/product-os (9 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,056 tokens. 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 2026-09-04.