refine

refine is a command for Claude Code from robisson/build-like-amazon-agent-skills. It costs 0 tokens per session (407 once invoked), scanned A, original, MIT.

A command for turning an early product idea into a PR/FAQ: a short press release and a set of questions with answers. Working Backwards is a planning method that starts with the customer benefit and works back toward the product.

In plain words
What is it for?
Use it to gather earlier planning work and write a launch-style press release plus customer and stakeholder FAQs.
Why use it?
It gives the idea a clear customer-focused shape and surfaces customer, internal, feasibility, cost, and timing questions before implementation.

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/refine
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 refine

README.md
[![agentmods](https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/refine.svg)](https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/refine)
Your own site
<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/refine"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/refine.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 407 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 $0.00000 $0.00407
Opus 5 $0.00000 $0.00204
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00041

Measured 5d ago against content hash 37a8ab694053, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refine 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/refine.md · 39 lines

What it actually says

Refine — Write the PR/FAQ

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-refine skill. This is Phase 4 of Working Backwards: crystallizing the idea into Amazon's PR/FAQ format.

What to do

  1. Read the skill file at skills/wb-refine/ for full context.
  2. Gather all previous artifacts (customer profile, problem statement, solution sketch).
  3. Write a PR/FAQ document with these sections:

Press Release (1 page max)

  • Headline: Customer benefit in <10 words
  • Subheadline: Who the customer is and what they get
  • Date and city: Imagined launch date
  • Opening paragraph: Problem, solution, benefit — crisp
  • How it works: 2-3 paragraphs of the customer experience
  • Quote from leader: Why this matters strategically
  • Quote from customer: Testimonial from the target persona
  • Call to action: How to get started

FAQ (2-5 pages)

  • Customer FAQ: Questions customers would ask (5-10)
  • Internal FAQ: Questions stakeholders would ask (5-10)
    • Feasibility, cost, timeline, dependencies, risks

Key Principles

  • Write for a general audience — no jargon.
  • If a FAQ answer is vague, the thinking isn't clear yet.
  • The PR/FAQ is a forcing function for clarity, not marketing fluff.
  • Iterate: most PR/FAQs go through 5+ revisions.

Output

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

Ask: "Would you like to proceed to /test-idea (validation plan)?"

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 · 39 lines · 0 tokens per session scan A 37a8ab694053

Subscribe to this mod's changes

refine 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 407 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.