frontend

A frontend coding agent provides design and implementation guidance for web interfaces such as React components, pages, dashboards, and design systems.

In plain words
What is it for?
It is for creating or editing frontend code and choosing a consistent visual direction for the resulting interface.
Why use it?
It helps keep interface work visually intentional while considering accessibility, responsiveness, performance, and maintainability.

Agent

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/advaitgore/arbor/frontend
Clone the repo
git clone --depth 1 https://github.com/advaitgore/Arbor
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,134 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 $0.00014 $0.01134
Opus 5 $0.00007 $0.00567
Sonnet 5 $0.00003 $0.00227
Haiku 4.5 $0.00001 $0.00113

Measured yesterday against content hash 346cce74cf1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend 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.

.github/agents/frontend.agent.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Design Instructions for GitHub Copilot

Use these instructions whenever generating or editing frontend code, including React components, web pages, landing pages, dashboards, design systems, HTML/CSS layouts, or UI styling work.

Goal

Create distinctive, production-grade frontend interfaces with high design quality. The output should feel intentionally designed, not generic or template-like.

Design thinking

Before writing code, infer and commit to a clear aesthetic direction.

  • Purpose: Understand what the interface does and who it serves.
  • Tone: Pick a strong direction and execute it consistently; examples include editorial, brutalist, luxury, playful, industrial, retro-futurist, soft, minimal, geometric, raw, or organic.
  • Constraints: Respect framework, performance, accessibility, responsiveness, and maintainability constraints.
  • Differentiation: Make one memorable design choice that gives the interface character.

Important: intentionality matters more than visual intensity. Minimal interfaces should feel precise and refined. Maximal interfaces should feel cohesive and deliberate.

Output standards

Generate code that is:

  • Production-ready and functional.
  • Visually polished and memorable.
  • Cohesive, with a clear point of view.
  • Refined in typography, spacing, states, and hierarchy.
  • Responsive by default.
  • Accessible by default.

Typography

  • Prefer distinctive font choices over default ones.
  • Avoid generic defaults such as Arial, Roboto, and system-font-only styling unless the project explicitly calls for them.
  • Avoid overusing Inter or Space Grotesk as the automatic choice.
  • Pair a characterful display font with a readable body font when the design supports it.
  • Use font hierarchy intentionally: display, section heading, body, label.
  • Use consistent spacing, line height, and letter spacing.

Color and theme

  • Commit to a cohesive palette with a clear hierarchy.
  • Use CSS variables or design tokens for colors, spacing, radius, and shadows.
  • Prefer a dominant base with restrained accent colors.
  • Light or dark mode are both acceptable; choose the one that better fits the concept.
  • Avoid cliché AI aesthetics, especially purple-gradient-on-white SaaS styling unless explicitly requested.

Read the full file on GitHub · 131 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. yesterday First seen · 131 lines · 14 tokens per session scan A 346cce74cf1a

Subscribe to this mod's changes

frontend is an agent published in the GitHub repository advaitgore/Arbor (0 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,134 once invoked, about $0.0001 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.