design-systems:review

design-systems:review is a skill for Claude Code from aaronbassett/agent-foundry. It costs 94 tokens per session (1,872 once invoked), scanned A, original, MIT.

A review skill that checks UI code against rules in a DESIGN.md file and looks for patterns associated with low-quality AI-generated interface code. It can scan CSS, SCSS, JSX, TSX, Vue, and Svelte files.

In plain words
What is it for?
Use it to audit a project's user-interface code for design-system compliance. It requires a DESIGN.md file or asks you to create one first.
Why use it?
It finds unauthorized colors, fonts, spacing, shadows, and component styles before they make the interface inconsistent.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the design-systems plugin — 4 skills shipped together

Good fit Use it to audit a project's user-interface code for design-system compliance. It requires a DESIGN.md file or asks you to create one first.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add aaronbassett/agent-foundry
Claude Code
/plugin install design-systems

Made for: Claude Code.

Or install design-systems, the plugin that ships this one along with the rest of its 4 skills.

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 design-systems:review

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronbassett/agent-foundry/review/github.svg)](https://agentmods.dev/skills/aaronbassett/agent-foundry/review)
Your own site
<a href="https://agentmods.dev/skills/aaronbassett/agent-foundry/review"><img src="https://agentmods.dev/badge/skills/aaronbassett/agent-foundry/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.

agentmods 80×15 button for design-systems:review

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaronbassett/agent-foundry/review"><img src="https://agentmods.dev/badge/skills/aaronbassett/agent-foundry/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,872 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 $0.00094 $0.01872
Opus 5 $0.00047 $0.00936
Sonnet 5 $0.00019 $0.00374
Haiku 4.5 $0.00009 $0.00187

Measured 9d ago against content hash 65d773871e87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-systems: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 9d 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/design-systems/skills/review/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Design System Compliance

Scan the project's UI code and produce a compliance report covering design system adherence and AI slop detection.

DESIGN.md Discovery

Find DESIGN.md using this search order:

  1. Check CLAUDE.md in cwd for a reference to DESIGN.md
  2. Look for DESIGN.md in cwd
  3. Search upward from cwd
  4. Search common locations: project root, src/, packages/*/
  5. If not found, tell the user: "No DESIGN.md found. Run /design-systems:create first."

Input

Optional argument: path to specific files or directory to review. Default: scan all UI code in the project.

Review Flow

Step 1: Parse Enforceable Rules

Extract from DESIGN.md:

Source What to Extract Use
Palette (Section 2) All hex values with token names Detect hardcoded colors outside the set
Type Scale (Section 3) Font families, weights Detect unauthorized fonts/weights
Spacing Scale (Section 4) All spacing values Detect off-scale spacing
Shadow Definitions (Section 5) Exact CSS shadow values Detect non-token shadows
Components (Section 6) Border-radius values Detect non-token radii
Core Prohibitions (Section 1) Each prohibition as a rule Custom check per prohibition

Step 2: Determine Scan Scope

Target file types: *.css, *.scss, *.jsx, *.tsx, *.vue, *.svelte

Exclude patterns:

  • node_modules/**
  • dist/**, build/**, .next/**, out/**
  • vendor/**
  • *.min.css, *.min.js

Use Glob to find files: **/*.{css,scss,jsx,tsx,vue,svelte}

If the user provided a specific path, scope to that path only.

Step 3: Design System Compliance Audit

For each DESIGN.md section, scan the codebase:

Colors (Section 2):

  • Grep for hex patterns: #[0-9a-fA-F]{3,8}
  • Also grep for rgb(, rgba(, hsl(, hsla( color declarations
  • Cross-reference each found value against the DESIGN.md palette
  • Flag any color not in the token set
  • Severity: CRITICAL if the color is explicitly banned (e.g., pure #000000 when prohibited), MODERATE otherwise

Read the full file on GitHub · 192 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. 9d ago First seen · 192 lines · 94 tokens per session scan A 65d773871e87

Subscribe to this mod's changes

design-systems:review is a skill published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 24d ago), licensed MIT. It adds 94 tokens to every session and 1,872 once invoked, about $0.0005 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 2026-08-31.