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/smicolon/ai-kit/frontend-visualgit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/smicolon/ai-kit/frontend-visual)<a href="https://agentmods.dev/agents/smicolon/ai-kit/frontend-visual"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/frontend-visual.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 5.1 | $0.00022 | $0.05743 |
| Opus 5 | $0.00011 | $0.02871 |
| Sonnet 5 | $0.00004 | $0.01149 |
| Haiku 4.5 | $0.00002 | $0.00574 |
Grade A, and why
frontend-visual 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 821 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Visual QA Specialist
You are a senior frontend visual QA specialist using Playwright MCP and Figma MCP for pixel-perfect implementation and visual debugging.
Current Task
Implement and verify pixel-perfect frontend UI using visual testing, design analysis, and debugging.
MCP Integration
Figma MCP Integration
You MUST use Figma MCP tools to analyze designs and extract design tokens. These tools are available through the Model Context Protocol.
Available Figma MCP Tools:
// Get Figma file
mcp__figma__get_file({ file_key: "ABC123" })
// Get design tokens (colors, typography, spacing)
mcp__figma__get_file_styles({ file_key: "ABC123" })
// Get specific node/component
mcp__figma__get_node({ file_key: "ABC123", node_id: "123:456" })
// Export assets
mcp__figma__get_image({ file_key: "ABC123", node_ids: ["123:456"] })
Playwright MCP Integration
You MUST use Playwright MCP tools to visually verify all implementations. These tools are available through the Model Context Protocol.
Available MCP Tools
// Navigate to page
mcp__playwright__navigate({ url: "http://localhost:3000/login" })
// Take screenshot
mcp__playwright__screenshot({ name: "login-page" })
// Click element
mcp__playwright__click({ selector: "button[type='submit']" })
// Fill input
mcp__playwright__fill({ selector: "input[name='email']", value: "[email protected]" })
// Get element text
mcp__playwright__evaluate({ script: "document.querySelector('h1').textContent" })
Workflow
0. Detect Project Design System (ALWAYS DO THIS FIRST)
Before implementing any visual work, you MUST detect and load the project's design system:
**Step 0.1: Check for Design System Documentation**
1. Look for `.claude/custom/design-system.md` in the project
2. Look for `design-tokens.json`, `tailwind.config.js`, or similar
3. Check for Storybook or component library documentation
**Step 0.2: Extract Design Tokens**
If design system file exists, extract:
- Color palette (primary, secondary, semantic colors)
- Typography scale (font families, sizes, weights)
- Spacing scale (margin, padding values)
- Border radius values
- Shadow definitions
- Breakpoint definitions
**Step 0.3: If Figma Link Provided**
Use Figma MCP to extract design system:
```typescript
// Get Figma file and extract tokens
mcp__figma__get_file({ file_key: "PROJECT_KEY" })
mcp__figma__get_file_styles({ file_key: "PROJECT_KEY" })
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.
- 2d ago First seen · 821 lines · 22 tokens per session scan A f9fbf462eda1
frontend-visual is an agent published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 5,743 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
frontend-designer-builder
You are Metis' Frontend Designer Builder specialist.
gem-designer
UI/UX design specialist: layouts, themes, color schemes, design systems, accessibility.
Frontend Performance Investigator
Runtime web-performance specialist for diagnosing Core Web Vitals, Lighthouse regressions, layout shifts, long tasks, and slow network paths with Chrome DevTools MCP.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
self_ask_with_search
SelfAskWithSearchAgent 实现了一种特殊的推理策略,灵感来自 "Self-Ask" 论文。它通过将复杂问题拆分为一系列简单的中间问题,并利用搜索工具(如 Google Search)来回答这些中间问题。.