figma-connect

figma-connect is a skill for Claude Code, Codex from haju-xp/figma-free-mcp. It costs 156 tokens per session (1,592 once invoked), scanned A, original, MIT.

A connector for the Figma desktop app's currently open file, using the figma-free-mcp plugin channel. It checks the relay, connects to the selected file and page, and diagnoses connection or installation problems.

In plain words
What is it for?
Use it to connect Figma, verify the connection, select among active files, and troubleshoot the Figma plugin setup.
Why use it?
It gives an agent a defined way to reach the Figma file you have open instead of a cloud file. It also helps distinguish missing plugins, inactive channels, and relay failures.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code.

Good fit Use it to connect Figma, verify the connection, select among active files, and troubleshoot the Figma plugin setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/haju-xp/figma-free-mcp/figma-connect
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.

Any agent
npx skills add haju-xp/figma-free-mcp --skill figma-connect
Clone the repo
git clone --depth 1 https://github.com/haju-xp/figma-free-mcp

Made for: Claude Code, Codex.

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-connect

README.md
[![agentmods](https://agentmods.dev/badge/skills/haju-xp/figma-free-mcp/figma-connect/github.svg)](https://agentmods.dev/skills/haju-xp/figma-free-mcp/figma-connect)
Your own site
<a href="https://agentmods.dev/skills/haju-xp/figma-free-mcp/figma-connect"><img src="https://agentmods.dev/badge/skills/haju-xp/figma-free-mcp/figma-connect/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 figma-connect

Your own site · 80×15
<a href="https://agentmods.dev/skills/haju-xp/figma-free-mcp/figma-connect"><img src="https://agentmods.dev/badge/skills/haju-xp/figma-free-mcp/figma-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,592 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00156 $0.01592
Opus 5.5 $0.00062 $0.00637
Sonnet 5.5 $0.00031 $0.00318
Haiku 4.5 $0.00016 $0.00159

Measured 7d ago against content hash e4f60d46c458, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figma-connect 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 7d 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.

Makes network callslowCapability

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

curl -s localhost:3055/channels
skills/figma-connect/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

피그마 연결

figma-free-mcp 플러그인 채널에 붙는다. 공식 Figma MCP(mcp.figma.com)는 쓰지 않는다.

figma-free-mcp (이 명령) 공식 Figma MCP
대상 데스크탑 앱에 지금 열려 있는 파일 클라우드의 Figma 파일
그리기 좌표·색·크기를 1px 단위로 직접 지정 자동 생성 — 세밀한 좌표 제어 불가

사용자는 명령어를 몰라도 된다. 아래 명령은 네가 실행한다. 승인 창이 뜨면 "허용을 눌러주세요"라고 한 번 알린다.

요청별 처리

"연결 확인"만 물었을 때

curl -s localhost:3055/channels

한 번만 실행하고 채널·접속 수만 답한다. 플러그인 호출이나 문서 조회는 하지 않는다 — 플러그인이 응답하지 않으면 그 호출들은 타임아웃까지 기다린다. 접속 수 2 = 플러그인과 Claude가 둘 다 붙은 상태, 1 = 플러그인만.

"연결해줘" / /figma-connect

  1. mcp__figma-free-mcp__auto_connect 를 부른다. 중계 서버가 꺼져 있으면 도구가 스스로 띄운다.
  2. 결과별로:
결과 할 일
Auto-connected to channel: … 3번으로
Relay server was just started … 서버를 방금 띄웠다. 사용자에게 "피그마에서 플러그인을 다시 실행해주세요"라고 요청 → 답을 받으면 auto_connect 재호출
No active Figma channels found "피그마 데스크탑 앱에서 작업할 파일을 열고 Plugins → Development → Figma Free MCP 를 실행해주세요" → 답을 받으면 재호출
채널 2개 이상 플러그인을 다시 열어서 생긴 이전 채널이 남은 것. list_active_channels 로 파일명을 보고, 애매하면 사용자에게 묻는다. 파일명을 알면 connect_to_file
WebSocket server not running (…) 자동 기동 실패. 아래 "점검"으로
피그마 도구 자체가 없음 설치가 안 됐거나 Claude Code 재시작 전. 아래 "설치"로

사용자 대신 Figma 화면을 조작하지 않는다.

  1. 붙은 뒤 mcp__figma-free-mcp__get_document_info 로 대상을 확인해 보고한다.
연결됨 — 채널 xxxx
파일: <파일명>
현재 페이지: <페이지명> (요소 N개)

현재 페이지에 이미 요소가 있으면 그대로 그리지 말고 물어본다.

"설치해줘" / "업데이트해줘"

node -v
npx -y figma-free-mcp@latest install
  • node -v 가 실패하면 멈추고 안내한다: https://nodejs.org 에서 LTS 설치(비밀번호는 사용자가 직접) → 터미널 재시작. Homebrew가 있으면 brew install node 는 네가 해도 된다.
  • install 이 하는 일: 모든 폴더에서 쓰이게 도구 등록, 피그마 플러그인 파일 복사, 이 스킬 설치, 예전 방식 잔재(폴더 전용 등록·전역 구버전) 정리, 플러그인 폴더 열기. 다시 실행하면 업데이트.
  • 끝나면 사용자에게 안내한다:
    1. (이 PC에서 처음일 때만) 피그마 데스크탑 앱 → Plugins → Development → Import plugin from manifest… → 방금 열린 폴더의 manifest.json 선택
    2. Claude Code를 껐다 켠다 — 도구는 시작할 때만 붙는다
    3. 그다음부터는 피그마에서 플러그인 실행 → /figma-connect

"점검해줘" — 뭔가 안 될 때

Read the full file on GitHub · 104 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. 7d ago First seen · 104 lines · 156 tokens per session scan A e4f60d46c458

Subscribe to this mod's changes

figma-connect is a skill published in the GitHub repository haju-xp/figma-free-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 156 tokens to every session and 1,592 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-02.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

build-ui-components-and-systems

A guide for building reusable UI components and design systems: shared visual rules, component interfaces, behavior, accessibility requirements, documentation, packaging, and version management. A design system is a maintained set of parts and rules that multiple screens or products can share.

EverMind-AI/Raven · 101 tokens