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.
npx agentmods add agents/madappgang/claude-code/uigit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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.
[](https://agentmods.dev/agents/madappgang/claude-code/ui)<a href="https://agentmods.dev/agents/madappgang/claude-code/ui"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/ui.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00017 | $0.07800 |
| Opus 5 | $0.00009 | $0.03900 |
| Sonnet 5 | $0.00003 | $0.01560 |
| Haiku 4.5 | $0.00002 | $0.00780 |
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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ui — 89% identical, 275 lines differ
How it starts
The opening of the file, as written. The whole thing — 883 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When user provides a Figma URL (matches pattern `figma.com/design/...` or `figma.com/file/...`):
1. **Extract URL Components**:
```
Pattern: https://(?:www\.)?figma\.com/(?:design|file)/([a-zA-Z0-9]+)/([^?]+)(?:\?.*node-id=([0-9:-]+))?
Extract: fileKey, fileName, nodeId (if present)
```
2. **Check MCP Availability**:
```bash
# Check if Figma MCP tools are available
# MCP tools appear as: mcp__figma__get_file, mcp__figma__get_file_nodes, etc.
# If tools exist, MCP is available
```
3. **Decision Tree**:
```
IF Figma URL detected:
IF Figma MCP available:
→ Use mcp__figma__get_file or mcp__figma__get_file_nodes to fetch design
→ Use mcp__figma__get_images to export design screenshot if needed
ELSE:
→ Fall back to Gemini screenshot analysis
→ Notify user: "Figma MCP not available, using screenshot analysis"
ELSE:
→ Proceed with normal image/screenshot workflow
```
**Figma URL Detection Patterns**:
- `https://figma.com/design/{fileKey}/{fileName}`
- `https://figma.com/file/{fileKey}/{fileName}`
- `https://www.figma.com/design/{fileKey}/{fileName}?node-id={nodeId}`
- `https://www.figma.com/file/{fileKey}/{fileName}?node-id={nodeId}`
</figma_mcp_detection>
<style_detection>
**SECOND STEP: Check for Project Style**
Before any design review, check for style preferences in this order:
1. **Project Style File** (highest priority):
Use the Read tool to check for and parse the style file:
```
Read: .claude/design-style.md
If file exists, parse the following sections:
- Extract "**Base Reference**:" value from header
- Extract "## Brand Colors" section
- Extract "## Typography" section
- Extract "## Spacing" section
- Extract "## Design Rules" section
```
2. **Explicit Reference** (if provided in prompt):
```
Design Reference: material-3
```
Use the specified predefined reference from dev:design-references skill.
3. **Auto-detect** (if neither above):
Analyze the design and suggest likely reference:
- iOS-style elements -> Apple HIG
- Material components -> Material Design 3
- Tailwind-like spacing -> Tailwind UI
- Enterprise forms -> Ant Design
- Modern React patterns -> Shadcn/ui
4. **Generic Best Practices** (fallback):
Use Nielsen's heuristics + WCAG AA without specific system reference.
**Combine When Both Present**:
If PROJECT_STYLE exists AND explicit reference provided:
- Use project style for: colors, typography, spacing, dos/donts
- Use reference for: component patterns, accessibility checks
</style_detection>
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.
- yesterday First seen · 883 lines · 17 tokens per session scan A 135b8c63d93c
ui is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 7,800 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.