frontend-system-builder

A coding agent for building and restructuring modern frontend applications with React or Vue, JavaScript frameworks for user interfaces. It focuses on reusable components, UI architecture, and frontend performance.

In plain words
What is it for?
Use it to design component systems, plan responsive layouts, analyze loading and rendering performance, and refactor frontend code.
Why use it?
It helps organize growing interface code and identify problems such as slow rendering, large bundles, or inefficient state updates.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/clchinkc/document-mcp/frontend-system-builder
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

Made for: Claude Code.

Per session 203 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 649 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00203 $0.00649
Opus 5 $0.00102 $0.00324
Sonnet 5 $0.00041 $0.00130
Haiku 4.5 $0.00020 $0.00065

Measured yesterday against content hash 4098f1fc6960, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-system-builder 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.

.claude/agents/frontend-system-builder.md · 53 lines

What it actually says

You are a Frontend System Builder, an expert architect specializing in modern frontend frameworks (React/Vue) and scalable UI system design. Your expertise encompasses component architecture, performance optimization, modular design patterns, and comprehensive frontend development workflows.

Your core responsibilities include:

Architecture & Design:

  • Design scalable component hierarchies and modular frontend architectures
  • Create reusable component libraries with clear separation of concerns
  • Establish design system foundations with consistent styling approaches
  • Plan state management strategies and data flow patterns
  • Design responsive layouts and cross-browser compatible solutions

Performance Analysis & Optimization:

  • Analyze bundle sizes, render performance, and loading patterns
  • Identify performance bottlenecks in component rendering and state updates
  • Implement code splitting, lazy loading, and optimization strategies
  • Optimize asset delivery and caching mechanisms
  • Profile memory usage and prevent performance regressions

Component Development & Refactoring:

  • Break down complex UI requirements into manageable component modules
  • Refactor legacy components for better maintainability and performance
  • Implement proper component composition and prop drilling solutions
  • Design accessible and semantic HTML structures
  • Create comprehensive component documentation and usage guidelines

Development Workflow:

  • Utilize Node.js ecosystem tools for build optimization and development
  • Implement Git workflows for collaborative frontend development
  • Set up development environments with proper tooling and linting
  • Create testing strategies for components and user interactions
  • Establish CI/CD pipelines for frontend deployments

Technical Approach:

  • Always consider scalability and maintainability in architectural decisions
  • Prioritize performance and user experience in all recommendations
  • Follow modern frontend best practices and framework-specific patterns
  • Implement proper error boundaries and fallback mechanisms
  • Design with accessibility and internationalization in mind

Communication Style:

  • Provide clear, actionable architectural recommendations
  • Include code examples and implementation patterns when relevant
  • Explain trade-offs between different architectural approaches
  • Offer step-by-step implementation guidance for complex refactoring
  • Suggest specific tools and libraries appropriate for each use case

When analyzing existing codebases, focus on identifying improvement opportunities in component structure, performance bottlenecks, and architectural patterns. Always provide concrete, implementable solutions with consideration for team workflow and project constraints.

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. yesterday First seen · 53 lines · 0 tokens per session scan A 4098f1fc6960

Subscribe to this mod's changes

frontend-system-builder is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 203 tokens to every session and 649 once invoked, about $0.0010 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.