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.
npx skills add robisson/build-like-amazon-agent-skills --skill wb-refinegit clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skillsWrote 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/skills/robisson/build-like-amazon-agent-skills/wb-refine)<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/wb-refine"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/wb-refine/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/skills/robisson/build-like-amazon-agent-skills/wb-refine"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/wb-refine.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 | $0.00064 | $0.04280 |
| Opus 5 | $0.00032 | $0.02140 |
| Sonnet 5 | $0.00013 | $0.00856 |
| Haiku 4.5 | $0.00006 | $0.00428 |
Grade A, and why
wb-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 10d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WB-Refine: The PR/FAQ
Overview
The PR/FAQ is Amazon's most iconic product development mechanism. It is a document (typically 6-12 pages) consisting of a Press Release (1-1.5 pages) and a Frequently Asked Questions section (4-10 pages). The press release is written as if the product already exists and is being announced to customers. The FAQ section answers the hardest questions — both from customers (external FAQ) and from leadership/stakeholders (internal FAQ).
The PR/FAQ is NOT a marketing document. It is a thinking tool. Writing forces precision. The press release format forces customer-centricity. The FAQ format forces you to confront uncomfortable questions before you've invested months of engineering effort.
A PR/FAQ typically goes through 10-20 revisions before approval. This is intentional. Each revision sharpens the thinking, closes logical gaps, and strengthens the argument. A first draft is never good enough — if it is, the author isn't being honest about the hard questions.
When to Use
- After completing Stage 3 (Invent) with a recommended solution
- As the primary decision artifact for any significant product investment
- When seeking leadership approval for resource allocation
- To align cross-functional teams (engineering, design, marketing, operations) on a shared vision
- When an existing initiative has lost clarity and needs to be re-grounded in customer value
Agent Persona
Load agents/doc-bar-raiser.md when reviewing the PR/FAQ. Use it to evaluate narrative clarity, customer specificity, FAQ rigor, and whether the document is strong enough to proceed to design.
Amazon Context
At Amazon, the PR/FAQ is read silently at the beginning of meetings. There are no presentations, no slides, no verbal pitches before reading. Everyone reads the document simultaneously (typically 20-30 minutes), then the discussion begins. This is deliberate:
- Silent reading equalizes information. Everyone has the same context, regardless of whether they got a "pre-read" or verbal briefing.
- Full sentences force complete thoughts. You can't hide behind bullet points in a narrative document.
- The author does the hard thinking, not the reader. In slide culture, the audience fills in the gaps. In document culture, the author must be explicit.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 296 lines · 64 tokens per session scan A e7dc18c2f40f
wb-refine is a skill published in the GitHub repository robisson/build-like-amazon-agent-skills (15 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 4,280 once invoked, about $0.0003 per session on Opus 5. 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.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…