A command that rates a codebase's design using scores for typography, color, spacing, animation, accessibility, and consistency. It explains each deduction using measured project data.

Use it to audit a design, compare versions before and after a redesign, or set a quality threshold in continuous integration.

It replaces an opinion-based design review with a repeatable report showing where the interface may be inconsistent or harder to use.

critique — Skill for Claude Code and Codex by Dragoon0x/dragoon-skills

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.

Any agent

npx skills add Dragoon0x/dragoon-skills --skill critique

Clone the repo

git clone --depth 1 https://github.com/Dragoon0x/dragoon-skills

Made for: Claude Code, Codex.

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/skills/dragoon0x/dragoon-skills/critique/github.svg)](https://agentmods.dev/skills/dragoon0x/dragoon-skills/critique)

Your own site

<a href="https://agentmods.dev/skills/dragoon0x/dragoon-skills/critique"><img src="https://agentmods.dev/badge/skills/dragoon0x/dragoon-skills/critique/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/skills/dragoon0x/dragoon-skills/critique"><img src="https://agentmods.dev/badge/skills/dragoon0x/dragoon-skills/critique.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 592 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	$0.00137	$0.00592
Opus 5.5	$0.00055	$0.00237
Sonnet 5.5	$0.00027	$0.00118
Haiku 4.5	$0.00014	$0.00059

Measured 1mo ago against content hash 95213a7b5067, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

critique 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/critique.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/critique/SKILL.md · 58 lines

What it actually says

/critique

0-100 scores for design quality. Transparent math. Every deduction is traceable to a metric in dragoon.json.

When to use

Run /critique when:

The user asks for a design quality score, audit, rating, or grade
Setting up a CI gate that fails when design quality drops below a threshold
Comparing design quality before and after a redesign
The user says "how good is this", "give me a score", "rate the design system"

What it produces

Six category scores plus an overall:

typography - font family count, scale ratio confidence, font size variant count
color - distinct color count, palette balance
spacing - grid detection confidence, spacing variant count
motion - easing variant count, duration variant count
accessibility - alt rate, button label rate, semantic tag presence
consistency - shadow variant count, radius variant count

Weighted overall:

typography 1.0  color 1.0  spacing 1.2  motion 0.8  accessibility 1.2  consistency 1.0

Each score includes a breakdown listing every deduction and reason. You can read exactly why your score is what it is.

Run it

node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js [root]

Flags:

--manifest <p> use existing manifest instead of scanning
--json machine-readable
--threshold <n> exit non-zero if overall score below n (CI gate)
--no-breakdown show scores only
--quiet show only the final score
--help full usage

Use as a CI gate

In package.json:

"design:check": "node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js --threshold 80 --quiet"

The command exits 1 if the overall score drops below 80, blocking the PR.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/critique.js 3.5 KB runs code

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.

1mo ago First seen · 58 lines · 137 tokens per session scan A 95213a7b5067

Subscribe to this mod's changes

critique is a skill published in the GitHub repository Dragoon0x/dragoon-skills (4 stars, last pushed 6mo ago), licensed MIT. It adds 137 tokens to every session and 592 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Claude Code Code review Design and UX accessibility agent-skills contrast-checker dark-mode design-tokens

ss-learn

Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…

bitjaru/styleseed · 73 tokens

html-artifact

Create self-contained HTML artifacts (single-file by default, split bundles when oversized) for complex, reviewable, or shareable work outputs. Use for an HTML artifact, browser-viewable report, implementation plan, PR/code-review report, dashboard, or mini deck, or for long Markdown-like outputs needing navigation or…

bahayonghang/my-ai-cli-toolkit · 80 tokens

role-ui-ux-designer

Use when orchestrating UI/UX design systems, anti-AI-slop frontend styling, tactile micro-interactions, responsive design tokens, accessibility standards, and high-fidelity interface engineering.

oyi77/1ai-skills · 44 tokens

ui-ux-scan

Quick UI/UX deficiency scan of any page. Checks touch targets, contrast, font consistency, spacing issues, empty states, loading indicators, and common UX anti-patterns. Uses Playwright MCP only — no signup.

Quality-Max/free-qa-skills · 50 tokens

accessibility-check

Quick WCAG accessibility scan of any URL. Checks color contrast, missing alt text, keyboard navigation, ARIA labels, heading hierarchy, and focus indicators. Produces a graded report. Uses Playwright MCP only — no signup.