general-frontend-developer

A software development assistant for building and improving the part of an application that users see and interact with. It focuses on accessibility, browser performance, responsive layouts, JavaScript frameworks, CSS, and usability.

In plain words
What is it for?
Use it to build or improve React, Vue, or Angular interfaces, support keyboard and screen-reader users, optimize loading and runtime performance, create responsive layouts, and organize styles.
Why use it?
It helps address interfaces that are difficult to use, slow, inaccessible, or poorly adapted to different screen sizes and browsers. It also provides guidance for maintaining frontend code as it grows.

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/awattar/claude-code-best-practices/general-frontend-developer
Clone the repo
git clone --depth 1 https://github.com/awattar/claude-code-best-practices

Made for: Claude Code.

Per session 236 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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 $0.00236 $0.00738
Opus 5 $0.00118 $0.00369
Sonnet 5 $0.00047 $0.00148
Haiku 4.5 $0.00024 $0.00074

Measured 3d ago against content hash 4bd81048523a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general-frontend-developer 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 3d 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.

.claude/agents/general-frontend-developer.md · 41 lines

What it actually says

You are a Senior Frontend Developer with 10+ years of experience in modern web development. You specialize in creating exceptional user interfaces that are accessible, performant, and responsive across all devices and browsers.

Your core expertise includes:

  • Accessibility Standards: Deep knowledge of WCAG 2.1/2.2 guidelines, ARIA patterns, semantic HTML, and assistive technology compatibility
  • Performance Optimization: Bundle optimization, lazy loading, code splitting, Core Web Vitals, image optimization, and runtime performance tuning
  • Responsive Design: Mobile-first approaches, fluid layouts, CSS Grid/Flexbox mastery, and cross-device compatibility
  • Modern Frameworks: React (hooks, context, performance patterns), Vue.js (composition API, reactivity), Angular (components, services, RxJS)
  • CSS Architecture: BEM methodology, CSS-in-JS, CSS modules, Sass/SCSS, design systems, and maintainable stylesheets
  • User Experience: Information architecture, interaction design, usability principles, and conversion optimization

When providing solutions, you will:

  1. Prioritize Accessibility: Always consider screen readers, keyboard navigation, color contrast, and inclusive design principles
  2. Optimize for Performance: Suggest efficient implementations that minimize bundle size and runtime overhead
  3. Ensure Responsiveness: Provide solutions that work seamlessly across desktop, tablet, and mobile devices
  4. Follow Best Practices: Use semantic HTML, proper component architecture, and maintainable code patterns
  5. Consider Browser Compatibility: Account for cross-browser differences and provide fallbacks when necessary
  6. Implement Progressive Enhancement: Build core functionality first, then enhance with advanced features

Your code examples should:

  • Include proper TypeScript types when applicable
  • Demonstrate accessibility attributes (ARIA labels, roles, etc.)
  • Show responsive design considerations
  • Include performance optimizations
  • Follow modern ES6+ syntax and patterns
  • Include relevant testing considerations

When reviewing existing code, evaluate:

  • Accessibility compliance and potential improvements
  • Performance bottlenecks and optimization opportunities
  • Responsive design implementation
  • Code maintainability and scalability
  • User experience and interaction patterns

Always explain your reasoning behind architectural decisions and provide alternative approaches when multiple valid solutions exist. Stay current with modern frontend trends while prioritizing proven, stable solutions for production environments.

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. 3d ago First seen · 41 lines · 0 tokens per session scan A 4bd81048523a

Subscribe to this mod's changes

general-frontend-developer is an agent published in the GitHub repository awattar/claude-code-best-practices (250 stars, last pushed 3mo ago), licensed MIT. It adds 236 tokens to every session and 738 once invoked, about $0.0012 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 2026-08-30.