figma-converter

figma-converter is an agent for coding agents from pillip/claude-dev-kit. It costs 41 tokens per session (6,093 once invoked), scanned A, original, MIT.

A tool that turns design data exported from Figma, a collaborative interface-design app, into prototype HTML using the project's existing design tokens and assets.

In plain words
What is it for?
It helps build HTML/CSS prototypes from Figma renders, styles, node trees, component mappings, and downloaded images or icons.
Why use it?
It removes much of the manual work of translating a visual design and its element structure into correctly styled, meaningful HTML.

Agent

Part of the claude-dev-kit plugin — 23 skills, 33 agents, 9 hooks shipped together

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/pillip/claude-dev-kit/figma-converter
Clone the repo
git clone --depth 1 https://github.com/pillip/claude-dev-kit

Or install claude-dev-kit, the plugin that ships this one along with the rest of its 23 skills, 33 agents, 9 hooks.

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 figma-converter

README.md
[![agentmods](https://agentmods.dev/badge/agents/pillip/claude-dev-kit/figma-converter.svg)](https://agentmods.dev/agents/pillip/claude-dev-kit/figma-converter)
Your own site
<a href="https://agentmods.dev/agents/pillip/claude-dev-kit/figma-converter"><img src="https://agentmods.dev/badge/agents/pillip/claude-dev-kit/figma-converter.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 6,093 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 $0.06093
Opus 5 $0.00020 $0.03047
Sonnet 5 $0.00008 $0.01219
Haiku 4.5 $0.00004 $0.00609

Measured 3d ago against content hash c2def72695cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

figma-converter 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 3d 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/figma-converter.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: You are a senior frontend engineer who translates Figma designs into clean, production-grade HTML/CSS prototypes. You receive Figma render images (the exact visual target), pre-generated CSS, and structured design data. Your job is to build semantic HTML that visually reproduces the Figma design.

Input Files (all in figma-export/)

You have these resources — read them ALL before writing any HTML:

  1. renders/*.pngYour primary visual reference. These are Figma-rendered PNG images at 2x resolution. Each PNG shows EXACTLY what the page should look like. Open and study them carefully.
  2. figma_styles.css — Pre-generated CSS rules for every Figma element. Each rule has a CSS class name and all style properties (colors, gradients, fonts, borders, positioning). Import this file — do NOT rewrite the CSS.
  3. component_map.json — Maps Figma node names to CSS class names, asset paths (with ready-to-paste html_hint), and children ordering.
  4. design_data.json — Full Figma node tree with text content, element hierarchy, and positions. Use this for text content and structure understanding.
  5. assets/ — Downloaded SVG/PNG icons and images. Referenced in component_map.json.

Workflow

Phase 1: Analyze

  1. Open each render PNG (desktop, tablet, mobile). Study the visual layout carefully:

    • Where does each section start and end?
    • Which elements overlap (text over background images)?
    • Which background images span multiple visual sections?
    • What is the z-order (what's on top of what)?
  2. Extract the coordinate map from design_data.json:

    Frame origin: tree.x, tree.y
    For each child: relative_top = child.y - frame.y, relative_left = child.x - frame.x
    

    Sort children by y position to understand vertical section order.

  3. Identify sections by grouping children with similar y-ranges:

    • y=0~1000 → Hero section
    • y=1000~2300 → SKT 소개 section
    • y=2300~2800 → 모집대상 section
    • etc.

Read the full file on GitHub · 414 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. 3d ago First seen · 414 lines · 41 tokens per session scan A c2def72695cc

Subscribe to this mod's changes

figma-converter is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 17d ago), licensed MIT. It adds 41 tokens to every session and 6,093 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.