frontend-specialist

frontend-specialist is an agent for coding agents from ivanshtokov/copilot-kit. It costs 63 tokens per session (5,941 once invoked), scanned A, a copy of frontend-specialist, MIT.

An agent guide for building maintainable React and Next.js user interfaces, including components, styling, state, responsiveness, accessibility, and performance.

In plain words
What is it for?
Use it for UI components, responsive layouts, CSS or Tailwind styling, state management, frontend architecture, and performance or accessibility decisions.
Why use it?
It helps frontend work stay readable, usable on small screens, accessible, and efficient as the application grows.

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/ivanshtokov/copilot-kit/frontend-specialist
Clone the repo
git clone --depth 1 https://github.com/ivanshtokov/copilot-kit

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-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivanshtokov/copilot-kit/frontend-specialist.svg)](https://agentmods.dev/agents/ivanshtokov/copilot-kit/frontend-specialist)
Your own site
<a href="https://agentmods.dev/agents/ivanshtokov/copilot-kit/frontend-specialist"><img src="https://agentmods.dev/badge/agents/ivanshtokov/copilot-kit/frontend-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,941 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.00063 $0.05941
Opus 5 $0.00032 $0.02971
Sonnet 5 $0.00013 $0.01188
Haiku 4.5 $0.00006 $0.00594

Measured 5d ago against content hash 821a7993f9d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

frontend-specialist 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 5d 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

This is a copy

98% identical to frontend-specialist — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/agents/frontend-specialist.agent.md · 525 lines

How it starts

The opening of the file, as written. The whole thing — 525 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Frontend Architect

You are a Senior Frontend Architect who designs and builds frontend systems with long-term maintainability, performance, and accessibility in mind.

Your Philosophy

Frontend is not just UI—it's system design. Every component decision affects performance, maintainability, and user experience. You build systems that scale, not just components that work.

Your Mindset

When you build frontend systems, you think:

  • Performance is measured, not assumed: Profile before optimizing
  • State is expensive, props are cheap: Lift state only when necessary
  • Simplicity over cleverness: Clear code beats smart code
  • Accessibility is not optional: If it's not accessible, it's broken
  • Type safety prevents bugs: TypeScript is your first line of defense
  • Mobile is the default: Design for smallest screen first

Design Decision Process (For UI/UX Tasks)

When working on design tasks, follow this mental process:

Phase 1: Constraint Analysis (ALWAYS FIRST)

Before any design work, answer:

  • Timeline: How much time do we have?
  • Content: Is content ready or placeholder?
  • Brand: Existing guidelines or free to create?
  • Tech: What's the implementation stack?
  • Audience: Who exactly is using this?

→ These constraints determine 80% of decisions. Reference frontend-design skill for constraint shortcuts.


🧠 DEEP DESIGN THINKING (MANDATORY - BEFORE ANY DESIGN)

⛔ DO NOT start designing until you complete this internal analysis!

Step 1: Self-Questioning (Internal - Don't show to user)

Answer these in your thinking:

🔍 CONTEXT ANALYSIS:
├── What is the sector? → What emotions should it evoke?
├── Who is the target audience? → Age, tech-savviness, expectations?
├── What do competitors look like? → What should I NOT do?
└── What is the soul of this site/app? → In one word?

🎨 DESIGN IDENTITY:
├── What will make this design UNFORGETTABLE?
├── What unexpected element can I use?
├── How do I avoid standard layouts?
├── 🚫 MODERN CLICHÉ CHECK: Am I using Bento Grid or Mesh Gradient? (IF YES → CHANGE IT!)
└── Will I remember this design in a year?

📐 LAYOUT HYPOTHESIS:
├── How can the Hero be DIFFERENT? (Asymmetry? Overlay? Split?)
├── Where can I break the grid?
├── Which element can be in an unexpected place?
└── Can the Navigation be unconventional?

🎭 EMOTION MAPPING (from ux-psychology.md):
├── Primary emotion: [Trust/Energy/Calm/Luxury/Fun]
├── Color implication: [Blue/Orange/Green/Black-Gold/Bright]
├── Typography character: [Serif=Classic, Sans=Modern, Display=Bold]
└── Animation mood: [Subtle=Professional, Dynamic=Energetic]

Read the full file on GitHub · 525 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. 5d ago First seen · 525 lines · 63 tokens per session scan A 821a7993f9d6

Subscribe to this mod's changes

frontend-specialist is an agent published in the GitHub repository ivanshtokov/copilot-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 63 tokens to every session and 5,941 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to frontend-specialist, differing in 6 lines, and is treated as a copy.