What is design-review?

A command for auditing the visual design and usability of a website from its URL. It captures desktop and mobile screenshots, evaluates ten design areas, and saves a written review.

Use it to review a website’s desktop and mobile experience, focus on a particular flow such as checkout, and compare the design with an industry reference.

It turns a website inspection into a repeatable report covering issues such as layout, text styling, color, spacing, and accessibility.

design-review — Command for Claude Code by MarcosNahuel

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/MarcosNahuel/antigravity-plugin-cc

Made for: Claude Code.

Or install antigravity, the plugin that ships this one along with the rest of its 2 skills, 22 commands, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/design-review/github.svg)](https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/design-review)

Your own site

<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/design-review"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/design-review"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 861 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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.00861
Opus 5	$0.00028	$0.00430
Sonnet 5	$0.00011	$0.00172
Haiku 4.5	$0.00006	$0.00086

Measured 10d ago against content hash eb6c4bbfebe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 10d 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.

plugins/antigravity/commands/design-review.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Route this to the antigravity:agy-rescue subagent in MODE: design-review.

Raw user request: $ARGUMENTS

Routing rules

Parse the URL: the first whitespace-separated token of $ARGUMENTS that starts with http:// or https:// IS the URL. If the user wrote it without a scheme, prepend https://. If no URL is found, ask once: "What URL should I review the design of?".
Focus: everything else in $ARGUMENTS is optional natural-language emphasis (e.g., "focus on the checkout flow on mobile", "compare against MercadoLibre seller backend"). Empty by default = full 10-dimension review at both viewports.
Slug: build from URL host + first path segment (lowercase, non-alphanumeric → -, collapse repeats, trim to 60 chars).
Date: today in YYYY-MM-DD.
Paths (relative to current working directory):
- OUTPUT_DIR = docs/agy/design-reviews/
- WRITE_FILE = docs/agy/design-reviews/<date>-<slug>.md
Pre-flight (ONE Bash call):
```
mkdir -p docs/agy/design-reviews
```

Hand off: pass this header to the subagent:

MODE: design-review
URL: <url>
FOCUS: <natural-language focus or empty>
CWD: <absolute path>
WRITE_FILE: docs/agy/design-reviews/<date>-<slug>.md

Operating rules

The subagent invokes agy with --add-dir <CWD> and a long timeout (12m0s) because design reviews involve browser navigation + multiple viewports + multimodal vision analysis.
The subagent reports:
1. Saved report path.
2. First ~30 lines (executive summary + design score).
3. Paths to captured screenshots (desktop + mobile).
Present that to the user as-is.
If the URL is blocked, returns non-200, or browser session crashes, surface the error verbatim.

What the review covers

Default 10-dimension audit:

Visual hierarchy
Typography (fonts, sizes, line-height, contrast)
Color system (palette, WCAG contrast, gradient usage)
Spacing & layout (grid, white space, alignment)
Interactive elements (button states, form affordance, micro-interactions)
Brand & tone (does design match the value-prop?)
Accessibility (alt text, focus indicators, ARIA, color contrast)
UX heuristics (Nielsen's 10)
Mobile/responsive behavior
Competitive context (if --focus includes a category, agy compares against industry standards)

Read the full file on GitHub · 77 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.

10d ago First seen · 77 lines · 57 tokens per session scan A eb6c4bbfebe5

Subscribe to this mod's changes

design-review is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (28 stars, last pushed 24d ago), licensed MIT. It adds 57 tokens to every session and 861 once invoked, about $0.0003 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.

Claude Code Design and UX anthropic antigravity claude-code-plugin deep-research gemini

design-review

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Routing rules

Operating rules

What the review covers

What this file has done since we first saw it

Other commands, from other repositories

theme

ux-audit

gemini-imagegen

phase-2-step-4

phase-2-step-5

audit-ux