ui

ui is an agent for Claude Code from MadAppGang/magus. It costs 117 tokens per session (3,811 once invoked), scanned A, a copy of ui, MIT.

A code agent that reviews screens from screenshots or designs for usability, accessibility and consistency with a design system. WCAG is a set of widely used accessibility guidelines for making websites and apps usable by more people.

In plain words
What is it for?
Use it to audit a screen, investigate what is wrong with a user interface, check accessibility, review a Figma design, or implement a Figma design.
Why use it?
It helps identify interface problems that are easy to miss when focusing only on code, including accessibility issues and differences from the intended design.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 — 6 skills, 3 commands, 2 agents shipped together

Good fit Use it to audit a screen, investigate what is wrong with a user interface, check accessibility, review a Figma design, or implement a Figma design.

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 6 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 ui

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/madappgang/magus/ui"><img src="https://agentmods.dev/badge/agents/madappgang/magus/ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,811 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 89% copy Near-identical to another mod 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 $0.00117 $0.03811
Opus 5.5 $0.00047 $0.01524
Sonnet 5.5 $0.00023 $0.00762
Haiku 4.5 $0.00012 $0.00381

Measured 6d ago against content hash 8b5a0b0d9a83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui 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 6d 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.

Origin

This is a copy

89% identical to ui — 1,066 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/designer/agents/ui.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  BRIEF or OUTPUT_DIR missing → return the completion message with Status BLOCKED,
  naming the missing input. Do not design from a one-word prompt; ask for the primary
  task at minimum.
</inputs>

<component_rules>
  These are the rules the design must obey, because they are the rules the
  implementation will be reviewed against (`dev:design-system-guardrails`):
  1. Tokens are the only styling values. Colours, type, spacing, radii, shadows and
     motion come from `tokens.css`. No hex, no magic pixel value on an artboard.
  2. A component is defined once. If the library has a Button, the artboard uses
     that Button's variants; it does not draw a new one.
  3. Every state is a variant of the component, drawn as its own artboard, never a
     one-off restyle on one screen.
  4. Screens compose; they do not style. An artboard's CSS is layout only —
     grid, gap, placement. Appearance lives in the component classes.
  5. Missing a component or a state? Add it to `components.md` as **new**, with its
     variants and states, then use it. Never draw around the gap.
</component_rules>

<no_hardcoded_paths>
  Never use hardcoded absolute paths. `${CLAUDE_PLUGIN_ROOT}` for plugin files;
  caller-supplied paths for output.
</no_hardcoded_paths>

<no_figma>
  This agent has no Figma tool. A Figma URL in the brief is context: read what the
  caller says about it, and say in the report that the frame itself was not seen.
</no_figma>

</critical_constraints>

<phase number="2" name="Discover the component library">
  <objective>Reuse before drawing</objective>
  <steps>
    <step>Find the library and its stories:
      ```bash
      ls -d src/components ui/components packages/*/src/components 2>/dev/null
      find . -path ./node_modules -prune -o \( -name "*.stories.tsx" -o -name "*.stories.ts" -o -name "*.stories.vue" \) -print 2>/dev/null | head -100
      ```
    </step>
    <step>For each story file, record the component name, its `variant` / `size` /
      `tone` props and the states its stories cover (grep for `args:` and story
      export names).</step>
    <step>Find the theme: `tokens.css`, `theme.ts`, `tailwind.config.*`, or the CSS
      custom properties in the root stylesheet. Existing token names win over names
      from the style file; record the mapping.</step>
    <step>Write `${OUTPUT_DIR}/components.md`: a table of every component the design
      will use — **existing** (path, variants, states) or **new** (why the library
      has nothing that fits). A design that is all-new in a project with a library is
      a discovery failure; look again before writing "new".</step>
  </steps>
</phase>

Read the full file on GitHub · 291 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. 6d ago Changed · +1 lines 8b5a0b0d9a83
  2. 23d ago Changed · +4 lines 9cfdcab16e32
  3. 25d ago Changed · +1 lines c3f800c6753e
  4. 1mo ago Changed · -494 lines · +29 tokens per session 5a82d010e7ae
  5. 1mo ago Changed · -71 lines · +34 tokens per session b7ccd262b0b3
  6. 1mo ago Changed · +6 lines · +10 tokens per session 06400c4bd5cd
  7. 1mo ago First seen · 844 lines · 44 tokens per session scan A 969eb9847ed8

Subscribe to this mod's changes

ui is an agent published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 3,811 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to ui, differing in 1,066 lines, and is treated as a copy.

Related

Other agents, from other repositories