Mimikyu: Instructions file for Claude Code

CLAUDE.md

Mimikyu CLAUDE.md is an instructions file for Claude Code from 3x-haust/Mimikyu. It costs 4,153 tokens per session, scanned A, original, MIT.

Repository instructions for Mimikyu, a tool that recreates Figma designs as React interfaces and checks screenshots for pixel-level differences.

In plain words
What is it for?
They help extract Figma data, build React and Tailwind screens, capture browser screenshots, compare pixels, and organize design files and test results.
Why use it?
They define the expected tools, folders, workflow, and verification process for design-to-code work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is 3x-haust/Mimikyu's own configuration. It tells Claude Code how to work on Mimikyu 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 Mimikyu configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is PORT=<port> npx tsx ../../scripts/screenshot.ts screenshots/v1.png <width> <height>.

Reuse

Borrowing it

Nothing to install: this file belongs to 3x-haust/Mimikyu. 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/3x-haust/Mimikyu/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/3x-haust/Mimikyu

Made for: Claude Code.

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 Mimikyu CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/3x-haust/mimikyu/claude-md/github.svg)](https://agentmods.dev/instructions/3x-haust/mimikyu/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/3x-haust/mimikyu/claude-md"><img src="https://agentmods.dev/badge/instructions/3x-haust/mimikyu/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Mimikyu CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/3x-haust/mimikyu/claude-md"><img src="https://agentmods.dev/badge/instructions/3x-haust/mimikyu/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,153 This file is loaded in full into every session.
When invoked 4,153 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.04153 $0.04153
Opus 5 $0.02076 $0.02076
Sonnet 5 $0.00831 $0.00831
Haiku 4.5 $0.00415 $0.00415

Measured yesterday against content hash dfa433f59af9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Mimikyu CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

#### 보조: curl 직접 호출 (MCP 불가 시 fallback)
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mimikyu (따라큐) - Figma Pixel Perfect Publisher

개요

Figma 디자인을 픽셀 퍼펙트하게 React + Tailwind CSS로 재현하는 도구. Figma MCP (Framelink + 공식)로 디자인 데이터를 추출하고, Playwright + PIL로 픽셀 단위 검증 루프를 돌린다.

프로젝트 구조

Mimikyu/
├── scripts/           # 공용 스크립트 (screenshot.ts, compare.py, mimikyu.ts, verify.ts)
└── <각 프로젝트>        # 폴더 구조 강제 없음 (아래 참조)

폴더 구조를 강제하지 않는다.

  • 사용자가 경로/기존 프로젝트/폴더 규칙을 주면 → 그대로 따른다 (기존 컨벤션을 존중, 엉뚱한 폴더 추가 금지).
  • 아무 정보가 없으면 → AI가 합리적인 구조를 스스로 정하고 진행한다. 물어보지 않고 진행 (예: 스택 네이티브 스캐폴드 + 앱 옆 designs/screenshots/diffs).
  • 사용자 정보 > AI 자율 판단.

기술 스택

  • React 19 + TypeScript + Tailwind CSS v4 (@tailwindcss/vite) + Vite
  • Playwright (headless Chromium 스크린샷)
  • Python PIL/Pillow (픽셀 비교 + 히트맵)
  • pnpm
  • Figma MCP 서버:
    • Framelink (framelink-figma) — get_figma_data, download_figma_images
    • 공식 Figma (figma) — view_node, add_figma_file, read_comments

워크플로우

Phase 1: Figma 디자인 데이터 추출 및 저장

MCP 도구를 사용하여 Figma 데이터를 가져오고, designs/figma-data.json에 저장한다. 이후 검증 루프에서는 MCP를 다시 호출하지 않고 이 파일을 참조하여 수정한다.

1. Framelink MCP — 디자인 구조 + 스타일 데이터
mcp__framelink-figma__get_figma_data(
  fileKey: "<FILE_KEY>",
  nodeId: "<NODE_ID>"    // URL의 node-id 파라미터
)
  • 레이아웃 구조, 스타일, 좌표, 타이포그래피 등 전체 디자인 데이터 반환
  • depth 옵션으로 트리 탐색 깊이 제어 가능
2. Framelink MCP — 이미지 에셋 다운로드
mcp__framelink-figma__download_figma_images(
  fileKey: "<FILE_KEY>",
  nodeId: "<NODE_ID>",
  outputDir: "public/assets/"
)
  • 아이콘, 일러스트 등 이미지 에셋을 로컬에 다운로드
3. 공식 Figma MCP — 노드 시각 확인
mcp__figma__view_node(
  file_key: "<FILE_KEY>",
  node_id: "<NODE_ID>"   // "1:46" 형식
)
  • 특정 노드의 썸네일 이미지 확인용
Figma URL 파싱
https://www.figma.com/design/<FILE_KEY>/Title?node-id=<NODE_ID>

추출할 데이터:

  • absoluteBoundingBox → 각 요소의 정확한 x, y, width, height
  • fills → 배경색, 그라디언트
  • style → font-family, font-size, font-weight, line-height, letter-spacing
  • cornerRadius → border-radius
  • effects → box-shadow
  • strokes → border
보조: curl 직접 호출 (MCP 불가 시 fallback)

Read the full file on GitHub · 319 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 Changed · +27 lines · +342 tokens per session dfa433f59af9
  2. 9d ago First seen · 292 lines · 3,811 tokens per session scan A 1513169d5ea0

Subscribe to this mod's changes

Mimikyu CLAUDE.md is an instructions file published in the GitHub repository 3x-haust/Mimikyu (25 stars, last pushed yesterday), licensed MIT. It adds 4,153 tokens to every session, about $0.0208 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens