design

design is a command for Claude Code from robisson/build-like-amazon-agent-skills. It costs 0 tokens per session (3,088 once invoked), scanned A, original, MIT.

A guided process for producing and reviewing a technical design before implementation, including dependencies, operations, APIs, security, and testing. It requires each stage's document to be produced and approved before the next stage.

In plain words
What is it for?
Use it to work from Working Backwards documents through design documentation, API contracts, threat modelling, review, and implementation specifications.
Why use it?
It makes important design decisions explicit and catches missing requirements, security risks, dependency problems, and operational gaps before coding begins.

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/design
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 design

README.md
[![agentmods](https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/design.svg)](https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/design)
Your own site
<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/design"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/design.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 3,088 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 $0.03088
Opus 5 $0.00000 $0.01544
Sonnet 5 $0.00000 $0.00618
Haiku 4.5 $0.00000 $0.00309

Measured 5d ago against content hash 7555b2a3e124, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

design 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/design.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design — Technical Design Document

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.

⛔ CRITICAL: Execute steps 1-5 IN ORDER. Each step MUST produce its artifact and receive user approval before the next step begins. If you find yourself writing specs without having produced a Design Document first, STOP — you are violating the process.

You are activating the design skill chain: dependency-managementfeature-flag-lifecycleoperational-excellencepatterns/ catalog → design-documentapi-contract-firstthreat-modelingdesign-reviewspec-driven-implementation.

What to do

  1. Read skills at skills/dependency-management/, skills/feature-flag-lifecycle/, skills/operational-excellence/, skills/design-document/, skills/api-contract-first/, skills/threat-modeling/, skills/design-review/, and skills/spec-driven-implementation/.
  2. Start from the Working Backwards artifacts in docs/working-backwards/ (if available).
  3. Guide the user through the design activities in sequence, with MANDATORY approval gates.

Step 0: State Detection + Proportionality Check

Before starting the full design flow, detect the project state and classify the change requested. The user should not have to think about which path is right — the agent decides, and asks only when there is genuine ambiguity.

  1. Read repo state:

    • Does docs/working-backwards/ exist with approved PR/FAQ or 5CQ?
    • Does docs/design/ already contain a Design Doc for the same feature?
    • Is the project a brownfield (significant code, IaC, CI present) without BLA artifacts, or a greenfield?
  2. Classify the requested change using the ladder in skills/using-amazon-skills/SKILL.md: Trivial / Small / Medium / Large / New product.

  3. Decide the path:

    State Change size Path
    WB artifacts exist (or user confirmed customer is known) Medium / Large / New product Proceed with the full Execution Order below.
    No WB artifacts, change is New product New product Tell the user /design should follow Working Backwards. Recommend /wb first.
    No WB artifacts, change is Medium or Large, greenfield medium / large Recommend /wb (or 5CQ) first to anchor on the customer. Use AskUserQuestion to confirm: [A] do /wb first, [B] proceed with assumed customer (risky), [C] cancel.
    No BLA artifacts at all, brownfield project any Use AskUserQuestion: [A] Run /onboard first to reverse-engineer the project (recommended), then come back to /design for the new change; [B] Proceed with /design from scratch (slower, may miss existing constraints); [C] Skip to /build if the change is Small or Trivial.
    Change is Trivial or Small trivial / small /design is overkill. Recommend going direct via /build instead. Confirm with the user before proceeding with the full flow.

Read the full file on GitHub · 149 lines

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 · 149 lines · 0 tokens per session scan A 7555b2a3e124

Subscribe to this mod's changes

design 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 3,088 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.