test-idea

test-idea is a command for Claude Code from robisson/build-like-amazon-agent-skills. It costs 0 tokens per session (385 once invoked), scanned A, original, MIT.

A planning command for testing an idea using Working Backwards, a method that starts with the intended customer outcome and works back to the plan. It defines assumptions, tests, and success measures.

In plain words
What is it for?
Use it to create a validation plan covering a minimum test, input and outcome measures, safeguards, targets, timelines, and stop criteria.
Why use it?
It turns a broad idea into a focused way to learn whether it works, including what must improve and when to stop.

Command for Claude Code

Part of the build-like-amazon plugin — 28 skills, 14 commands, 10 agents shipped together

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.

agentmods
npx agentmods add commands/robisson/build-like-amazon-agent-skills/test-idea
Clone the repo
git clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skills

Made for: Claude Code.

Or install build-like-amazon, the plugin that ships this one along with the rest of its 28 skills, 14 commands, 10 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 test-idea

README.md
[![agentmods](https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/test-idea.svg)](https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/test-idea)
Your own site
<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/test-idea"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/test-idea.svg" alt="Measured on agentmods" 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 385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00385
Opus 5 $0.00000 $0.00192
Sonnet 5 $0.00000 $0.00077
Haiku 4.5 $0.00000 $0.00038

Measured 5d ago against content hash fbcde1f05eea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

test-idea 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 5d 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/test-idea.md · 35 lines

What it actually says

Test Idea — How Will We Measure Success?

Path resolution: All skills/, agents/, and patterns/ paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.

You are activating the wb-test-and-iterate skill. This is Phase 5 of Working Backwards: defining how to validate the idea and measure its impact.

What to do

  1. Read the skill file at skills/wb-test-and-iterate/ for full context.
  2. Review the PR/FAQ and solution sketch from previous phases.
  3. Help the user define a validation and metrics plan:
    • What are the key assumptions that must be true for this to succeed?
    • How can we test each assumption cheaply and quickly?
    • What does the MVP look like? (minimum to learn, not minimum to ship)
    • What metrics prove we're solving the problem?
  4. Write a Success Metrics document with:
    • Input metrics (what we control: adoption, usage, features shipped)
    • Output metrics (what we hope to move: satisfaction, time saved, errors reduced)
    • Guardrail metrics (what must NOT get worse)
    • Target values and measurement timeline
    • Kill criteria (when do we stop if it's not working?)

Key Principles

  • Measure outcomes, not outputs — "customer success" not "features shipped."
  • Every metric needs a baseline, target, and deadline.
  • Prefer leading indicators over lagging ones.
  • Design experiments that can fail — unfalsifiable tests teach nothing.
  • Two-pizza team should own the metrics end-to-end.

Output

Save to docs/working-backwards/<feature-name>/success-metrics.md.

Ask: "Working Backwards is complete. Ready to /design the technical solution?"

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. 5d ago First seen · 35 lines · 0 tokens per session scan A fbcde1f05eea

Subscribe to this mod's changes

test-idea is a command published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 385 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 2026-08-30.