build

build is a command for Claude Code from robisson/build-like-amazon-agent-skills. It costs 0 tokens per session (5,669 once invoked), scanned A, original, MIT.

A command that carries out previously approved software specifications from start to finish. It organizes the work by specifications, dependency waves, and parallel tasks.

In plain words
What is it for?
Implementing all approved specs, running their tasks in dependency order, and performing an automatic review after each spec.
Why use it?
It removes the need to pause for approval between implementation steps after the design has already been approved.

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/build
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 build

README.md
[![agentmods](https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/build.svg)](https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/build)
Your own site
<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/build"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/build.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 5,669 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 $0.05669
Opus 5 $0.00000 $0.02835
Sonnet 5 $0.00000 $0.01134
Haiku 4.5 $0.00000 $0.00567

Measured 5d ago against content hash cd868a0985fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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/build.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build — Execute Specs

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.

⛔ Default Execution Mode: Fully Autonomous Until the Feature Is Done

Unlike /design and /wb, /build runs without human gates by default. The approval gates happened before /build (during spec creation in /design). Once specs exist and are approved, /build executes everything end-to-end.

When the user invokes /build (with no other instruction), the agent MUST:

  1. Read all specs in specs/ and identify the execution order (hardest-first, established during /design).
  2. Execute every spec in order, end-to-end, without pausing between specs and without asking permission to continue.
  3. Within each spec, execute all waves wave-by-wave per the dependency graph, without pausing between waves.
  4. Within each wave, dispatch all tasks in parallel as sub-agents, without pausing between tasks.
  5. After each spec, run the Post-Implementation Review automatically (see end of this file). If verdict is PASSED or PASSED WITH FIXES NEEDED, proceed to the next spec without asking. Only FAILED stops execution to surface to the user.
  6. Stop only when all specs in specs/ are in a terminal state (every task [x] or [!]). At that point, present a single end-of-build summary.

When to stop and ask the user (the only valid reasons)

The agent MAY only stop autonomous execution when one of these is true:

  • Hard blocker: a sub-agent reports [!] blocked and the blocker requires human input (missing credential, missing upstream service, ambiguous design that needs clarification, etc.). Mark the task [!] with reason and present.
  • Failed Post-Implementation Review: verdict is FAILED (fundamentally wrong implementation, requirement entirely unimplemented, architectural gap). Present implementation-review.md and wait for guidance.
  • Green-build gate fails and cannot self-recover: tests broken in a way that cannot be fixed with a follow-up task within scope.
  • The user explicitly asked to pause/checkpoint (see override below).

Read the full file on GitHub · 334 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 · 334 lines · 0 tokens per session scan A cd868a0985fd

Subscribe to this mod's changes

build 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 5,669 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.