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-writeup.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-writeup)<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/experiment-writeup"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/experiment-writeup/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-writeup"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/experiment-writeup.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 | $0.02781 |
| Opus 5 | $0.00000 | $0.01391 |
| Sonnet 5 | $0.00000 | $0.00556 |
| Haiku 4.5 | $0.00000 | $0.00278 |
Grade A, and why
experiment-writeup 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Writeup
Analyse the results of an experiment and produce a structured writeup with learnings and a clear decision recommendation.
Experiment: $ARGUMENTS
Important: Run the entire analysis in one pass. Do NOT pause for user input until the final step.
Step 0: Find the experiment doc
- Search
projects/for a file matching the experiment name or description - If no match, search
projects/subdirectories and check file contents - If still no match, ask the user for the file path and stop
Read the experiment doc and extract:
- Hypothesis — what was being tested and why
- Primary metric — the success measure
- Secondary metrics — supporting measures
- Guardrail metrics — what must not get worse
- Decision rules — pre-committed criteria for ship / iterate / kill
- Audience — who was in the experiment, how traffic was split
- Run time — how long it ran, expected sample size
- ROTI — if calculated, the expected return on time invested
If any of these are missing from the doc, flag it: "The experiment doc is missing [X] — this makes rigorous analysis harder. Recommend adding this to future experiments."
Step 1: Gather results data
Check for results in this order:
- Existing results doc — look for a results file alongside the experiment doc (e.g.
*-results.md,*-analysis.md) - Project folder — check for any data files, CSVs, or analysis docs in the same directory
- BigQuery — if no pre-existing results, use
/dbt-data-source-researcherto identify relevant tables and pull key metrics - Ask the user — if data isn't available in any of the above, state what data is needed and ask the user to provide it
Also check:
data/reports/for relevant WBR data covering the experiment periodinsights/quant/for any related quantitative analysis- Granola (via MCP) for post-experiment meeting transcripts that may contain analyst findings
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 · 252 lines · 0 tokens per session scan A 8c9c216156cc
experiment-writeup 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 2,781 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.