design-review

design-review is an agent for Claude Code from MadAppGang/magus. It costs 47 tokens per session (6,242 once invoked), scanned A, original, MIT.

A visual checking tool that compares a design from Figma, an image, or a web page with a screenshot of the built interface. It creates a structured report of visual differences and can also assess whether the differences make sense.

In plain words
What is it for?
Use it to check web pages against design files or reference pages before release, and to document visual mismatches for correction.
Why use it?
It helps find where an implementation does not match the intended design, including small visual differences that are easy to miss during manual review.

Agent for Claude Code

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

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 designer plugin — 5 skills, 3 commands, 2 agents shipped together

Good fit Use it to check web pages against design files or reference pages before release, and to document visual mismatches for correction.

Compare 6 agents 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 MadAppGang/magus
Claude Code
/plugin install designer

Made for: Claude Code.

Or install designer, the plugin that ships this one along with the rest of its 5 skills, 3 commands, 2 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 design-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/madappgang/magus/design-review/github.svg)](https://agentmods.dev/agents/madappgang/magus/design-review)
Your own site
<a href="https://agentmods.dev/agents/madappgang/magus/design-review"><img src="https://agentmods.dev/badge/agents/madappgang/magus/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.

agentmods 80×15 button for design-review

Your own site · 80×15
<a href="https://agentmods.dev/agents/madappgang/magus/design-review"><img src="https://agentmods.dev/badge/agents/madappgang/magus/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,242 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00047 $0.06242
Opus 5 $0.00023 $0.03121
Sonnet 5 $0.00009 $0.01248
Haiku 4.5 $0.00005 $0.00624

Measured 5d ago against content hash 5b77d4118885, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -f -o "${OUTPUT_DIR}/reference-raw.png" "${IMAGE_URL}"
plugins/designer/agents/design-review.md · 700 lines

How it starts

The opening of the file, as written. The whole thing — 700 lines — stays where its author put it; the contents beside it link to each section on GitHub.

    <step>Generate RUN_ID if not provided:
      ```bash
      RUN_ID="ui-val-$(date -u +%Y%m%d-%H%M%S)-$(head -c 2 /dev/urandom | xxd -p)"
      ```
    </step>

    <step>Create output directory if not already provided:
      ```bash
      if [ -n "${SESSION_PATH}" ]; then
        OUTPUT_DIR="${SESSION_PATH}/ui-validation/${RUN_ID}"
      else
        OUTPUT_DIR=".ui-validation/${RUN_ID}"
      fi
      mkdir -p "${OUTPUT_DIR}"
      ```
    </step>

    <step>Verify bun is available:
      ```bash
      which bun || echo "not_found"
      ```
      If not found: stop with error "bun not found in PATH. Install from https://bun.sh"
    </step>

    <step>Initialize Tasks with all workflow phases</step>
  </steps>
</phase>

<phase number="1" name="Detect Reference and Implementation Types">
  <objective>Determine input types and validate sources</objective>
  <steps>
    <step>Determine REFERENCE_TYPE from REFERENCE_SOURCE:
      - Contains "figma.com/design/" or "figma.com/file/" → REFERENCE_TYPE = "figma"
      - Starts with "http://" or "https://" (and not figma) → REFERENCE_TYPE = "browser"
      - Otherwise → REFERENCE_TYPE = "image"
    </step>

    <step>For figma type: parse FIGMA_FILE_KEY and FIGMA_NODE_ID:
      - Pattern for fileKey: /figma\.com\/(?:design|file)\/([A-Za-z0-9]+)/
      - Pattern for nodeId: /[?&]node-id=([0-9A-Za-z%-]+)/
      - Normalize nodeId: replace '%3A' with ':' and '-' with ':'
    </step>

    <step>Determine IMPL_TYPE from IMPL_SOURCE:
      - Starts with "http://" or "https://" → IMPL_TYPE = "url"
      - Otherwise → IMPL_TYPE = "file"
    </step>
  </steps>
</phase>

<phase number="2" name="Capture Reference Image">
  <objective>Obtain the reference image into OUTPUT_DIR/reference-raw.png</objective>

  <branch name="figma">
    <step>Verify Figma MCP availability by checking if mcp__figma__get_file_nodes is available.
      If unavailable: stop with error:
      "ERROR: Figma MCP not available.
       To configure:
       1. Add FIGMA_ACCESS_TOKEN to your environment
       2. Ensure figma MCP is listed in your .mcp.json
       3. Restart Claude Code to reload MCP servers"
    </step>

    <step>Fetch structured design data:
      ```
      mcp__figma__get_file_nodes(
        fileKey: FIGMA_FILE_KEY,
        nodeIds: [FIGMA_NODE_ID]
      )
      ```
      From the response, extract and store as FIGMA_TOKENS:
      - colors: all fill and stroke styles as hex values
      - typography: font family, size, weight, line height per text node
      - spacing: padding, margin, gap from auto-layout properties
      - nodeMap: [{nodeId, name, absoluteBoundingBox}] for all leaf nodes
    </step>

Read the full file on GitHub · 700 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 Changed · +12 lines 5b77d4118885
  2. 10d ago First seen · 688 lines · 47 tokens per session scan A 2ca2db3f8796

Subscribe to this mod's changes

design-review is an agent published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 6,242 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

Design System Auditor

Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…

Community-Access/accessibility-agents · 109 tokens

design

Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.

Rune-kit/rune · 35 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens

frontend-reviewer

Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.

everywan-dev/claude-code-engineering · 28 tokens