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 skills add LeekJay/claude-skills-plugin --skill frontend-architecture-designgit clone --depth 1 https://github.com/LeekJay/claude-skills-pluginWrote 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/skills/leekjay/claude-skills-plugin/frontend-architecture-design)<a href="https://agentmods.dev/skills/leekjay/claude-skills-plugin/frontend-architecture-design"><img src="https://agentmods.dev/badge/skills/leekjay/claude-skills-plugin/frontend-architecture-design/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.
<a href="https://agentmods.dev/skills/leekjay/claude-skills-plugin/frontend-architecture-design"><img src="https://agentmods.dev/badge/skills/leekjay/claude-skills-plugin/frontend-architecture-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00080 | $0.02411 |
| Opus 5 | $0.00040 | $0.01205 |
| Sonnet 5 | $0.00016 | $0.00482 |
| Haiku 4.5 | $0.00008 | $0.00241 |
Grade A, and why
frontend-architecture-design 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 10d 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Architecture Design & Review
Comprehensive frontend project architecture review from five key dimensions: performance, maintainability, scalability, engineering, and type safety.
Decision Framework
Default behavior: For architecture review tasks, prefer Sub-Agent mode for thorough analysis.
🔴 Mandatory Sub-Agent Triggers (ANY ONE triggers delegation)
- Full architecture review: User requests comprehensive/complete architecture analysis
- Multi-dimension analysis: Needs evaluation across 2+ dimensions (performance, maintainability, etc.)
- Large codebase: Project has 50+ components or 100+ source files
- Redesign request: User mentions "redesign", "restructure", "overhaul", "major refactor"
- Migration planning: Evaluating tech stack migration or major upgrades
- Performance audit: Deep performance analysis with metrics collection
- Report generation: User wants a formal architecture review report
- Comparison analysis: Comparing old vs new architecture, or multiple approaches
🟢 Main Conversation Handling (ALL conditions must be met)
- Single dimension: Only checking one specific aspect (e.g., "check TypeScript config")
- Quick question: Simple questions like "is this pattern okay?" or "what's wrong with this structure?"
- Small scope: Looking at 1-3 specific files or components
- No report needed: Just need quick feedback, not a formal report
Decision Flow
Check for ANY 🔴 mandatory trigger?
├─ YES → ✅ USE SUB-AGENT MODE immediately
│ subagent_type="frontend-architecture-design:frontend-architecture-design"
└─ NO → Check if ALL 🟢 simple conditions are met?
├─ YES → Handle in main conversation
└─ NO → ✅ USE SUB-AGENT MODE (default behavior)
Quick Reference Examples
| User Description | Trigger Signal | Decision |
|---|---|---|
| "Review the frontend architecture" | 🔴 Full review | Sub-Agent |
| "Is this component structure okay?" | 🟢 Quick question, small scope | Main conversation |
| "Analyze performance and maintainability" | 🔴 Multi-dimension | Sub-Agent |
| "Check my tsconfig settings" | 🟢 Single dimension, small scope | Main conversation |
| "We need to restructure the app" | 🔴 Redesign request | Sub-Agent |
| "What's wrong with this import?" | 🟢 Quick question | Main conversation |
| "Generate an architecture report" | 🔴 Report generation | Sub-Agent |
| "Should I use barrel exports?" | 🟢 Quick question | Main conversation |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 350 lines · 80 tokens per session scan A 84ae366d625b
frontend-architecture-design is a skill published in the GitHub repository LeekJay/claude-skills-plugin (4 stars, last pushed 9mo ago), licensed MIT. It adds 80 tokens to every session and 2,411 once invoked, about $0.0004 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.
Other skills, from other repositories
ui-toolkit/web
Reference skill for Zoom Video SDK UI Toolkit. Use after routing to a web video workflow when you want prebuilt React UI instead of building a fully custom Video SDK interface.
zoom-meeting-sdk-web-component-view
Zoom Meeting SDK Web - Component View. Embeddable Zoom meeting components with Promise-based API for flexible integration. Ideal for React/Vue/Angular apps and custom layouts. Uses ZoomMtgEmbedded with async/await patterns and embeddable UI containers.
astro
Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.
tanstack-form
Headless, performant, and type-safe form state management for TS/JS, React, Vue, Angular, Solid, Lit, and Svelte.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
web-development
Use when users need to implement, integrate, debug, build, deploy, or validate a Web frontend after the product direction is already clear, especially for React, Vue, Vite, browser flows, or CloudBase Web integration.