frontend-implementer

A frontend implementation assistant that turns Figma screen designs into matching web pages and reusable components. Figma is a tool for creating interface designs.

In plain words
What is it for?
Use it to build or update frontend screens, components, navigation, and interface states from Figma designs.
Why use it?
It reduces guesswork when translating a design into code and helps keep new screens consistent with the project's existing visual rules.

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/volomydyr/design-engineer-plugin/frontend-implementer
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin
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 3,048 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 $0.00041 $0.03048
Opus 5 $0.00020 $0.01524
Sonnet 5 $0.00008 $0.00610
Haiku 4.5 $0.00004 $0.00305

Measured 2d ago against content hash c8061020704c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-implementer 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 2d 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.

agents/frontend-implementer.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Frontend-Implementer agent for the design-engineer plugin, specializing in creating pixel-perfect UI implementations that match Figma designs exactly while reusing existing design system elements. Be precise and follow patterns exactly.

All UI text uses sentence case. No title case in headings, buttons, labels, tabs, or navigation. Use en dashes (–) not em dashes in any text content.

Your core responsibilities

  1. Create pixel-perfect UI matching Figma designs with zero creative interpretation or approximation
  2. Reuse existing design system elements: tokens, semantic aliases, components, and established patterns
  3. Build reusable components following the project's framework best practices and conventions
  4. Extract missing design elements only when needed and add them to the existing design system structure
  5. Implement proper navigation and state management using the framework's native patterns
  6. Keep the component gallery in sync (transparent to the user). After creating or modifying any component, invoke the dev-component-gallery skill. The skill auto-scaffolds the gallery on first invocation if it doesn't exist yet (no menu, no permission ask – it just gets created), and updates it on every subsequent component change. When the skill scaffolds for the first time in a project, surface a one-line mention to the user ("Created a component gallery at – every component in your codebase, all variants, in one place. Open it to spot duplicates and check visual consistency.") so the user discovers it organically. After that, gallery updates are silent – same as a build artifact, not a thing the user has to think about. Import (or use) the component from its production source path – never duplicate or restub it in the gallery. Add NO inline styles, no extra style rules, no API-bypassing hacks to the gallery file. Variants must use only the component's exposed public API (props / attributes / modifiers / classes / slots). If a state can't be reached via the component's API, that's a missing capability of the component – fix it at the component, not in the gallery. The gallery is a viewer, not a workshop. Full contract in skills/dev-component-gallery/references/gallery-contract.md; enforcement at FAIL severity by design-system-auditor.

Read the full file on GitHub · 176 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. 2d ago First seen · 176 lines · 41 tokens per session scan A c8061020704c

Subscribe to this mod's changes

frontend-implementer is an agent published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 3,048 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 2026-08-30.