build-like-amazon-agent-skills: Instructions file for Claude Code

CLAUDE.md

build-like-amazon-agent-skills CLAUDE.md is an instructions file for Claude Code from robisson/build-like-amazon-agent-skills. It costs 2,560 tokens per session, scanned A, original, MIT.

Project instructions for a structured engineering workflow based on Amazon's Working Backwards method, where teams start from customer needs and work toward implementation. It also defines slash commands such as /onboard and /wb and requires approval gates.

In plain words
What is it for?
Use it for project onboarding, Working Backwards design cycles, API planning, threat-model work, and other defined command-based workflows.
Why use it?
It gives the agent a consistent process for understanding existing projects, designing work, and making decisions that require approval.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is robisson/build-like-amazon-agent-skills's own configuration. It tells Claude Code how to work on build-like-amazon-agent-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything build-like-amazon-agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to robisson/build-like-amazon-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/robisson/build-like-amazon-agent-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skills

Made for: Claude Code.

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 build-like-amazon-agent-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robisson/build-like-amazon-agent-skills/claude-md.svg)](https://agentmods.dev/instructions/robisson/build-like-amazon-agent-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/robisson/build-like-amazon-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/robisson/build-like-amazon-agent-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,560 This file is loaded in full into every session.
When invoked 2,560 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02560 $0.02560
Opus 5 $0.01280 $0.01280
Sonnet 5 $0.00512 $0.00512
Haiku 4.5 $0.00256 $0.00256

Measured 7d ago against content hash 483d4a0510ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

build-like-amazon-agent-skills CLAUDE.md 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 7d 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.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

You are operating in a project that uses Build Like Amazon Agent Skills — a structured set of engineering workflows based on Amazon's Working Backwards methodology and operational excellence culture.

Skills Directory

All skills are located in skills/. Each skill is a directory with a SKILL.md file (and optionally templates/). Agent personas are in agents/.

Use skills/using-amazon-skills/SKILL.md as the meta-skill when the user does not invoke a slash command and the right workflow is unclear. It routes ambiguous requests to the correct lifecycle phase and skill chain.

Slash Commands

When the user invokes a slash command, read the corresponding command file in .claude/commands/ and follow it:

Command Command File What It Does
/onboard .claude/commands/onboard.md Reverse-engineer an existing project — produce Design Doc, API contracts, baseline Threat Model from existing code, IaC, observability. Run once per brownfield project. 3 paths: anchor only / validate the why (inferred PR/FAQ + bar-raiser questions) / forward WB + gap analysis.
/wb .claude/commands/wb.md Full Working Backwards cycle (5 stages with approval gates)
/listen .claude/commands/listen.md Stage 1: Who is the customer?
/define .claude/commands/define.md Stage 2: What is the problem?
/invent .claude/commands/invent.md Stage 3: What is the solution?
/refine .claude/commands/refine.md Stage 4: Write the PR/FAQ
/test-idea .claude/commands/test-idea.md Stage 5: How will we measure success?
/design .claude/commands/design.md Full design flow (Dependency/Flag/Ops Context → Design Doc → API → Threat Model → Review → Specs)
/spec .claude/commands/spec.md Create a single new spec (when design already exists)
/build .claude/commands/build.md Execute spec tasks (wave-by-wave, parallel, autonomous)
/review .claude/commands/review.md Code review with bar raiser mentality
/deploy .claude/commands/deploy.md Progressive deployment with auto-rollback
/operate .claude/commands/operate.md Operational readiness and runbook generation
/learn .claude/commands/learn.md COE — blameless post-incident analysis

Read the full file on GitHub · 141 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. 7d ago First seen · 141 lines · 2,560 tokens per session scan A 483d4a0510ae

Subscribe to this mod's changes

build-like-amazon-agent-skills CLAUDE.md is an instructions file published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It adds 2,560 tokens to every session, about $0.0128 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens