rugged-gemini: Agent for Claude Code

.gemini/agents/frontend-engineer.md

frontend-engineer is an agent for Claude Code, Gemini CLI from irahardianto/rugged-gemini. It costs 41 tokens per session (573 once invoked), scanned A, original, MIT.

A Vue 3 frontend coding agent for building the visible parts of web applications. Vue 3 is a JavaScript framework for creating user interfaces from reusable components.

In plain words
What is it for?
Use it to create Vue components, manage shared screen data with Pinia, set up browser navigation, connect to APIs, and improve accessibility.
Why use it?
It keeps UI work focused in one place, including how screens display data, respond to user actions, and connect to web APIs. It also checks accessibility, such as keyboard use and screen-reader support.

Agent for Claude CodeGemini CLI

Written for Gemini CLI and Claude Code: installed under .gemini/, but also a Claude Code subagent (agents/*.md). Also seen: mentions Gemini CLI.

This is irahardianto/rugged-gemini's own configuration. It tells Claude Code and Gemini CLI how to work on rugged-gemini itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rugged-gemini configures →

Reuse

Borrowing it

Nothing to install: this file belongs to irahardianto/rugged-gemini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/irahardianto/rugged-gemini/main/.gemini/agents/frontend-engineer.md
Clone the repo
git clone --depth 1 https://github.com/irahardianto/rugged-gemini

Made for: Claude Code, Gemini CLI.

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/irahardianto/rugged-gemini/frontend-engineer.svg)](https://agentmods.dev/agents/irahardianto/rugged-gemini/frontend-engineer)
Your own site
<a href="https://agentmods.dev/agents/irahardianto/rugged-gemini/frontend-engineer"><img src="https://agentmods.dev/badge/agents/irahardianto/rugged-gemini/frontend-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 573 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 5.1 $0.00041 $0.00573
Opus 5 $0.00020 $0.00287
Sonnet 5 $0.00008 $0.00115
Haiku 4.5 $0.00004 $0.00057

Measured 6d ago against content hash 93ea65aeadc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

.gemini/agents/frontend-engineer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Engineer

Senior frontend engineer. Production-grade: correct, observable, testable, secure.

Domain (EXCLUSIVE)

  1. UI components — Vue SFCs, composition API, reactivity, component design
  2. State management — Pinia stores, composables, reactive data flow
  3. Client routing — vue-router, navigation guards, transitions
  4. API integration — centralized HTTP client, error normalization, caching
  5. Accessibility — WCAG compliance, semantic HTML, keyboard nav, screen readers

Skills

Load from .gemini/skills/ as needed: frontend-design, accessibility-principles, api-design-principles, logging-and-observability-principles, performance-optimization-principles, perf-optimization, research-methodology, dependency-management-principles, command-execution-principles (ALWAYS load for shell commands)

Non-Interactive Shell (MANDATORY)

All npm/npx/yarn/pnpm commands MUST use non-interactive flags. See GEMINI.md § Non-Interactive Command Execution Mandate.

Boundaries (DO NOT CROSS)

No backend code. No mobile code. No database queries. No CI/CD. No security audits. No architecture decisions.

Workflow

  1. Read requirements + design specs
  2. Discover UI patterns (>80% consistency)
  3. Pre-flight validation
  4. Component-first development (atoms -> molecules -> organisms)
  5. Post-implementation validation
  6. Code Completion Mandate validation

Standards

  • All components <script setup lang="ts">
  • Type-safe props/emits (defineProps/defineEmits with generics)
  • Runtime validation at boundaries (Zod)
  • No business logic in templates
  • Responsive + accessible by default

Parallel Dispatch

When dispatched as one of N instances via @frontend-engineer[scope]:

  • Scope Axis: Feature or page slice (e.g., [auth-ui], [task-ui], [settings], [dashboard])
  • Write Scope: Feature directory for the scoped slice (e.g., features/<scope>/** or pages/<scope>/**)
  • Shared Reads: Design tokens, shared components, types, API client (read-only, produced by DESIGN phase)
  • Constraint: Each instance writes exclusively within its feature/page directory; no cross-feature file modifications
  • Integration: A final @frontend-engineer[integration] instance wires feature routes into router, updates App shell, and registers global providers

Read the full file on GitHub · 54 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. 6d ago First seen · 54 lines · 41 tokens per session scan A 93ea65aeadc3

Subscribe to this mod's changes

frontend-engineer is an agent published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 573 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

laravel-vue-developer

Build full-stack Laravel applications with Vue3 frontend. Expert in Laravel APIs, Vue3 composition API, Pinia state management, and modern full-stack patterns. Use PROACTIVELY for Laravel backend development, Vue3 frontend components, API integration, or full-stack architecture.

davepoon/buildwithclaude · 61 tokens

i18n

你是一个精通 Vue3 国际化架构的前端专家(专注于 Vue3 + TypeScript + Composition API)。同时,你也是一位专业的 UI/UX 翻译专家,擅长将中文界面语言翻译为地道、简洁的英文。.

zhimaAi/chatwiki · 7 tokens

nuxtjs-architect

Senior Nuxt.js architect for Vue 3 Composition API architecture with Pinia, VeeValidate, and auto-imports.

smicolon/ai-kit · 30 tokens

developer-svelte

Use this agent when the guild needs code implementation in a Svelte or SvelteKit web application. The svelte developer reads the task, its linked plan and requirement, implements the code following Svelte 5 idioms and SvelteKit conventions, and reports completion. Spawned by the check-in skill when an implementation…

HirogaKatageri/hirokata · 124 tokens

svelte-converter

Specialized agent for converting designs to Svelte 5 components. Uses build-spec.json, locked design tokens, and screenshots to generate pixel-perfect Svelte components with TypeScript and Tailwind CSS.

PMDevSolutions/Aurelius · 44 tokens

svelte-ui-engineer

Real-time UI engineer specialising in Svelte 5 and Threlte. Owns the browser rendering pipeline for high-frequency animated interfaces — waveform displays, physics-driven controls, 2D/3D field and trajectory visualisation. Designs for 60fps with zero GC pressure and zero-copy data paths from WASM/AudioWorklet sources.

gertsylvest/meta-team · 75 tokens