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.
curl -O https://raw.githubusercontent.com/motorway-sandbox/product-os/main/.claude/commands/experiment-setup.mdgit clone --depth 1 https://github.com/motorway-sandbox/product-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/commands/motorway-sandbox/product-os/experiment-setup)<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/experiment-setup"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/experiment-setup/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/commands/motorway-sandbox/product-os/experiment-setup"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/experiment-setup.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 | $0.00000 | $0.02706 |
| Opus 5 | $0.00000 | $0.01353 |
| Sonnet 5 | $0.00000 | $0.00541 |
| Haiku 4.5 | $0.00000 | $0.00271 |
Grade A, and why
experiment-setup 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 4d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Setup
Generate a complete experiment setup recommendation for a proposed experiment. This command cross-references past experiments, estimates the right success metric, calculates sample size and run time, scores revenue potential (ROTI), and produces a ready-to-use experiment parameters section for the project doc.
Arguments
The user should provide one of:
- A description of the proposed experiment (what they want to test and where)
- A path to an existing project/experiment doc that needs setup parameters
- A hypothesis in "If X, then Y, because Z" format
If insufficient context is provided, ask for: the intervention point (which funnel step), the hypothesised mechanism, and the engineering estimate (days).
Instructions
Phase 1: Past experiment lookup
Before calculating anything, search for similar past experiments to ground the analysis in evidence.
-
Search the Notion Experimentation Tracker using
mcp__claude_ai_Notion__notion-searchagainst the data source{your-experiment-tracker-collection-id}. Search by:- Location of test — find experiments at the same funnel step (e.g. {your funnel steps, e.g. Sign-up page, Onboarding, Activation, Checkout})
- Lever — find experiments using the same psychological/UX mechanism (e.g. Credibility, Effort, Trust, Urgency, User flow, Social Proof)
- Pillar/Squad — find experiments from the same team area
-
Fetch the top 3-5 most relevant completed experiments using
mcp__claude_ai_Notion__notion-fetchand read their content for detailed metrics (funnel uplift, ARR impact, learnings). -
Search Hex using
mcp__claude_ai_Hex__search_projectsfor experiment result dashboards with detailed analysis. -
Check local experiment docs in
projects/for full writeups with statistical analysis.
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.
- 4d ago First seen · 220 lines · 0 tokens per session scan A 6b5de65f0452
experiment-setup 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 2,706 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.