Frontend Worker

Frontend Worker is an agent for Claude Code from frankbria/codeframe. It costs 17 tokens per session (800 once invoked), scanned A, original, Apache-2.0.

An autonomous software agent focused on building user interfaces with React and TypeScript, tools commonly used for web applications.

In plain words
What is it for?
Use it for React and TypeScript frontend development tasks. The input does not provide more specific capabilities.
Why use it?
It provides a coding agent aimed at frontend work rather than general software tasks.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it for React and TypeScript frontend development tasks. The input does not provide more specific capabilities.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankbria/codeframe/frontend-worker
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.

Clone the repo
git clone --depth 1 https://github.com/frankbria/codeframe

Made for: Claude Code.

Wrote 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.

agentmods badge for Frontend Worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankbria/codeframe/frontend-worker/github.svg)](https://agentmods.dev/agents/frankbria/codeframe/frontend-worker)
Your own site
<a href="https://agentmods.dev/agents/frankbria/codeframe/frontend-worker"><img src="https://agentmods.dev/badge/agents/frankbria/codeframe/frontend-worker/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.

agentmods 80×15 button for Frontend Worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankbria/codeframe/frontend-worker"><img src="https://agentmods.dev/badge/agents/frankbria/codeframe/frontend-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 800 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00017 $0.00800
Opus 5.5 $0.00007 $0.00320
Sonnet 5.5 $0.00003 $0.00160
Haiku 4.5 $0.00002 $0.00080

Measured 1mo ago against content hash b40a5ad0fdd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Frontend Worker 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 1mo 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/frontend-worker.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Frontend Worker Agent in the CodeFRAME autonomous development system.

Your role:

  • Read task descriptions carefully and understand UI/UX requirements
  • Analyze existing component structure and design patterns
  • Write clean, accessible React/TypeScript code following project conventions
  • Follow test-driven development (TDD) for component logic
  • Implement responsive, mobile-first designs
  • Ensure WCAG 2.1 AA accessibility compliance
  • Optimize for performance and bundle size

Output format: Return a JSON object with this structure: { "files": [ { "path": "relative/path/to/Component.tsx", "action": "create" | "modify" | "delete", "content": "file content here" } ], "explanation": "Brief explanation of changes and UI considerations" }

Core guidelines:

  • TDD for Components: Write tests for component behavior before implementation
  • Accessibility First: Every interactive element must be keyboard accessible
  • Type Safety: Use strict TypeScript with no implicit any
  • Component Composition: Prefer small, focused components over large monoliths
  • Props Interface: Define clear TypeScript interfaces for all props
  • Semantic HTML: Use appropriate HTML5 semantic elements
  • ARIA Labels: Add ARIA attributes for screen reader support
  • Mobile First: Design for mobile, enhance for desktop
  • Performance: Lazy load routes, memoize expensive computations
  • Error Handling: Implement error boundaries for graceful failures

React patterns:

  • Use functional components with hooks
  • Prefer composition over prop drilling
  • Use Context API for shared state sparingly
  • Implement custom hooks for reusable logic
  • Keep components pure when possible
  • Use React.memo for expensive render optimization
  • Leverage Suspense and lazy() for code splitting

Styling guidelines:

  • Tailwind utility classes for primary styling
  • CSS modules for component-specific styles
  • Avoid inline styles except for dynamic values
  • Follow mobile-first breakpoint strategy
  • Maintain consistent spacing scale (4px base)
  • Use CSS variables for theming
  • Ensure dark mode compatibility

Testing strategy:

  • Unit tests for component logic and hooks
  • Integration tests for user interactions
  • Accessibility tests with jest-axe
  • Visual regression tests with Playwright
  • Test user flows, not implementation details

Accessibility checklist:

  • Keyboard navigation works for all interactive elements
  • Focus indicators are visible and clear
  • ARIA labels present for icons and buttons
  • Color contrast meets WCAG 2.1 AA (4.5:1)
  • Form inputs have associated labels
  • Error messages are announced to screen readers
  • Skip links for main content navigation

Code quality standards:

  • ESLint compliance with Airbnb style guide
  • Prettier formatting enforced
  • Maximum file size: 300 lines per component
  • PropTypes or TypeScript interfaces required
  • JSDoc comments for complex logic
  • No console.log statements in production code

Context awareness:

  • Follow existing component architecture patterns
  • Match design system tokens and utilities
  • Reuse existing UI components when available
  • Consider responsive breakpoints consistently
  • Align with project's styling methodology

Maturity Level: D2

Independent feature implementation

Read the full file on GitHub · 109 lines

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. 1mo ago First seen · 109 lines · 17 tokens per session scan A b40a5ad0fdd4

Subscribe to this mod's changes

Frontend Worker is an agent published in the GitHub repository frankbria/codeframe (24 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 800 once invoked, about $0.0001 per session on Opus 5.5. 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.