onboard

onboard is a command for Claude Code from robisson/build-like-amazon-agent-skills. It costs 0 tokens per session (1,851 once invoked), scanned A, original, MIT.

A command for discovering how an existing software project works and creating reference documents from its code, infrastructure, and monitoring setup.

In plain words
What is it for?
Mapping a project, documenting its APIs and threats, reconstructing why it exists, and preparing it for specification or implementation work.
Why use it?
It gives later development work a reliable picture of the current system, including its interfaces, risks, and missing rationale.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

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

Good fit Mapping a project, documenting its APIs and threats, reconstructing why it exists, and preparing it for specification or implementation work.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/robisson/build-like-amazon-agent-skills/onboard
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.

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.

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 onboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/onboard.svg)](https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/onboard)
Your own site
<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/onboard"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/onboard.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 1,851 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01851
Opus 5 $0.00000 $0.00925
Sonnet 5 $0.00000 $0.00370
Haiku 4.5 $0.00000 $0.00185

Measured 7d ago against content hash 33f11938ec7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

onboard 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/commands/onboard.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboard — Reverse-Engineer an Existing Project

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.

/onboard activates the brownfield-discovery skill. It runs once per project (or when the project drifts significantly) and produces anchoring artifacts derived from the real code, IaC, and observability.

/onboard has three paths, picked by the user at the start. The agent classifies and asks; the user picks an outcome, not a process step.

Path Outcome Time
A — Anchor only (default, recommended) Design Doc + API contracts + Threat Model from existing code. No customer/PR/FAQ. ~15–30min
B — Validate the why Path A + reverse-engineered PR/FAQ + hard questions from doc-bar-raiser where the code can't tell us why ~30–45min
C — Forward WB + Gap Analysis Full canonical /wb from scratch (5 stages with gates, agent reading existing code) + Path A + gap-analysis.md ~1–2h

The output anchors all subsequent /spec and /build invocations — instead of re-discovering the project on every change, the agent reads the persisted artifacts.

When to Use

  • The project already has significant code, IaC, CI, and possibly observability — but no Build Like Amazon artifacts (docs/design/, docs/working-backwards/)
  • A medium or large change is coming, and anchoring the agent on the real state of the project will pay back many times
  • The user explicitly invokes /onboard
  • The project has drifted significantly from the prior reverse-engineered baseline (architecture change, major refactor, new pattern adopted)
  • The user wants to validate that what's been built actually serves a real customer problem (Path B)
  • The project is pivoting / re-strategizing and the user wants to re-derive the WB from scratch and see the gap (Path C)

When NOT to Use

Read the full file on GitHub · 120 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 · 120 lines · 0 tokens per session scan A 33f11938ec7f

Subscribe to this mod's changes

onboard 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 1,851 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.