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 design-reviewgit 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/design-review)<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/design-review"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/design-review/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/design-review"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/design-review.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 | $0.00040 | $0.02435 |
| Opus 5 | $0.00020 | $0.01218 |
| Sonnet 5 | $0.00008 | $0.00487 |
| Haiku 4.5 | $0.00004 | $0.00244 |
Grade A, and why
Design Review 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 11d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
Overview
Design Review is a quality gate before spec-driven-implementation and /build. Its purpose is to catch design flaws while they are still cheap to fix in a document instead of expensive to fix in code or production.
This is not a meeting format, SLA, or panel process. For an agent, the job is straightforward: evaluate whether the design is clear, complete, simple, operable, and safe enough to become executable specs. If the design does not meet the bar, block progression and explain exactly what must change.
When to Use
- Before creating implementation specs from a design document
- Before implementing a new service, major component, public API, shared library, infrastructure change, or data model change
- When the design introduces new external dependencies, queues, caches, databases, third-party APIs, or cross-service calls
- When the design changes security boundaries, access models, customer data handling, or operational blast radius
- When a decision is a one-way door or would be expensive to reverse after implementation
Amazon Context
Amazon-style design review raises the bar by forcing written reasoning before implementation. The reviewer evaluates the design on behalf of the customer and the long-term operators of the system, not on behalf of delivery pressure.
A strong review does not try to prove the author wrong. It makes the design better by surfacing missing assumptions, weak trade-offs, hidden failure modes, operational gaps, and unnecessary complexity.
The Process
Before reviewing, load agents/design-bar-raiser.md and apply that persona's review lens. If the design contains a one-way door decision, also load agents/principal-engineer.md and apply that persona to the irreversible decision, blast-radius, and long-term architecture trade-off review.
1. Context Assessment
Before reviewing, classify the design:
- Is this a one-way door? Public API, data migration, security model, data deletion, service split/merge, or irreversible infrastructure change.
- Does it introduce or change external dependencies? Services, databases, caches, queues, config systems, or third-party APIs.
- Does it handle customer, Confidential, or Restricted data?
- Does it affect other teams, shared infrastructure, or public consumers?
- Does it add operational burden, new alarms, new runbooks, or new on-call failure modes?
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.
- 11d ago First seen · 216 lines · 40 tokens per session scan A d35705328953
Design Review is a skill published in the GitHub repository robisson/build-like-amazon-agent-skills (15 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 2,435 once invoked, about $0.0002 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
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
agent-design-best-practices
Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…