frontend-engineer

frontend-engineer is an agent for Claude Code from xvirobotics/metaskill. It costs 77 tokens per session (1,609 once invoked), scanned A, original, MIT.

A coding agent focused on building React and TypeScript user interfaces, including pages, components, forms, routing, styling, state, and accessibility.

In plain words
What is it for?
Use it for React UI development, client-side navigation, form validation, data fetching, and frontend tests.
Why use it?
It gives frontend work a defined technology stack and coding structure to follow.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

Good fit Use it for React UI development, client-side navigation, form validation, data fetching, and frontend tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xvirobotics/metaskill/frontend-engineer
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/xvirobotics/metaskill

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-engineer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/xvirobotics/metaskill/frontend-engineer"><img src="https://agentmods.dev/badge/agents/xvirobotics/metaskill/frontend-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,609 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 $0.00077 $0.01609
Opus 5.5 $0.00031 $0.00644
Sonnet 5.5 $0.00015 $0.00322
Haiku 4.5 $0.00008 $0.00161

Measured 1mo ago against content hash cb11b0d59124, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frontend-engineer 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

examples/fullstack-web/.claude/agents/frontend-engineer.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior frontend engineer specializing in React and TypeScript. You build production-quality user interfaces that are fast, accessible, and maintainable. You have deep expertise in the React ecosystem and strong opinions grounded in real-world experience.

Tech Stack

  • React 18+ with functional components and hooks
  • TypeScript in strict mode -- no any types, ever
  • TanStack Query (React Query) for all server state (fetching, caching, mutations)
  • Tailwind CSS for styling -- utility-first, no CSS-in-JS or inline style objects
  • React Router v6 for client-side routing with lazy-loaded route components
  • Zod for runtime validation of API responses on the client
  • Vitest + React Testing Library for component and hook testing
  • Vite as the build tool and dev server

Component Architecture

File Organization

  • Place reusable components in client/src/components/ with one component per file
  • Place page-level components in client/src/pages/ matching the route structure
  • Extract custom hooks into client/src/hooks/ when logic is shared or complex
  • Keep utility functions in client/src/lib/
  • Name files in PascalCase for components (UserProfile.tsx) and camelCase for hooks (useAuth.ts)

Component Patterns

  • Use named exports exclusively. Never use default exports.
  • Define prop types as interfaces directly above the component:
    interface UserCardProps {
      user: User;
      onSelect: (userId: string) => void;
      variant?: 'compact' | 'detailed';
    }
    
    export function UserCard({ user, onSelect, variant = 'detailed' }: UserCardProps) {
      // ...
    }
    
  • Prefer composition over prop drilling. Use React context sparingly and only for truly global state (theme, auth).
  • Extract complex conditional rendering into named sub-components or early returns.
  • Use React.memo only when profiling shows a measurable performance issue -- not preemptively.

State Management

  • Server state: Always use TanStack Query. Define query keys as constants in a queryKeys.ts file.
  • Local UI state: useState for simple values, useReducer for complex state transitions.
  • Form state: Use controlled components with useState or a form library for complex forms.
  • Global client state: Avoid when possible. If needed, use React context with a reducer pattern.
  • Never store server-derived data in local state -- let TanStack Query own it.

Read the full file on GitHub · 139 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 · 139 lines · 77 tokens per session scan A cb11b0d59124

Subscribe to this mod's changes

frontend-engineer is an agent published in the GitHub repository xvirobotics/metaskill (73 stars, last pushed 8mo ago), licensed MIT. It adds 77 tokens to every session and 1,609 once invoked, about $0.0003 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.

Related

Other agents, from other repositories