Borrowing it
Nothing to install: this file belongs to tkhr-sait/penpot-selfhost-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tkhr-sait/penpot-selfhost-mcp/main/.claude/skills/penpot/SKILL.mdgit clone --depth 1 https://github.com/tkhr-sait/penpot-selfhost-mcpWrote 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.
[](https://agentmods.dev/skills/tkhr-sait/penpot-selfhost-mcp/penpot)<a href="https://agentmods.dev/skills/tkhr-sait/penpot-selfhost-mcp/penpot"><img src="https://agentmods.dev/badge/skills/tkhr-sait/penpot-selfhost-mcp/penpot/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.
<a href="https://agentmods.dev/skills/tkhr-sait/penpot-selfhost-mcp/penpot"><img src="https://agentmods.dev/badge/skills/tkhr-sait/penpot-selfhost-mcp/penpot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.04557 |
| Opus 5 | $0.00043 | $0.02278 |
| Sonnet 5 | $0.00017 | $0.00911 |
| Haiku 4.5 | $0.00009 | $0.00456 |
Grade A, and why
penpot 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Penpot MCP Integration
ユーザーのリクエスト内容に応じてルーティングし、必要なリファレンスを Read して実行する。 Claude Code では $ARGUMENTS、OpenCode ではスキルロード時のユーザーメッセージが対象。
ツール名規約
本スキルではツールを以下の短縮名で参照する。MCP サーバー名は penpot-official。呼び出し時のプレフィックスはプラットフォームが自動付与する（Claude Code: mcp__penpot-official__、opencode: penpot-official_ 等）。利用可能なツール一覧から短縮名に一致するものを使用すること。
| 短縮名 | 用途 |
|---|---|
activate |
セッション開始・metrics 取得 |
execute_code |
Penpot 操作実行 |
export_shape |
シェイプ画像エクスポート |
penpot_api_info |
API 型情報取得 |
high_level_overview |
API 概要取得 |
| penpot-manage.sh | bash .claude/skills/penpot/scripts/penpot-selfhost/penpot-manage.sh |
execute_codeは Penpot MCP サーバー（penpot-official）のツールを使用すること。IDE の Jupyter 実行ツールとの混同に注意。penpot-manage.shは上記パスで bash 実行。
初期化: activate を呼び出してセッション開始（storage ラッパー自動初期化）。ルートごとに「Read」列のファイルを Read する。
ルーティングマップ
リファレンスパスは本スキルディレクトリ（
.claude/skills/penpot/）からの相対パス。
| キーワード | セクション | 実行 | Read |
|---|---|---|---|
| なし / 起動 / 設定 / 利用可能にして | 環境セットアップ | 親AI直接 | selfhost.md |
| 停止 / down / status / ログ | 環境セットアップ（コマンド実行） | 親AI直接 | — |
| DS構築 / トークン定義 / テーマ / ダーク / ライト | デザインシステム構築 | penpot-mcp | mcp-api.md, design.md + フェーズ誘導で該当ファイル |
| コンポーネント / ライブラリ | DS構築（Phase 04-05） | penpot-mcp | mcp-api.md, design.md, workflow/phase-04 or 05, library-architecture.md |
| デザイン / 画面 / UI / プロトタイプ | デザイン作成 | penpot-mcp | mcp-api.md, howto/, design.md |
| アプリ作成 / コード生成 / コード変換 | アプリケーション作成 | penpot-mcp | pipeline/overview.md, mcp-api.md |
| トークン同期 / DTCG | 外部パイプライン（01） | penpot-mcp | mcp-api.md, pipeline/01-token-sync.md |
| SD / CSS変数 / SCSS | 外部パイプライン（02） | 親AI直接 | pipeline/02-style-dictionary.md |
| Storybook | 外部パイプライン（03） | 親AI直接 | pipeline/03-storybook.md |
| VRT / Lost Pixel | 外部パイプライン（04） | 親AI直接 | pipeline/04-vrt.md |
| パイプライン / 外部連携 | 外部パイプライン（全体） | penpot-mcp | pipeline/overview.md |
| レビュー / デザイン検証 | デザインレビュー | penpot-mcp | mcp-api.md, comments.md |
| コメント | コメント操作 | penpot-mcp | comments.md |
| その他 | 引数内容に応じて判断 | — | — |
What ships with it
52 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/core/comments.md 7.9 KB
- reference/core/delegation-format.md 11 KB
- reference/core/design.md 9.0 KB
- reference/core/library-architecture.md 4.8 KB
- reference/core/mcp-api.md 28 KB
- reference/core/selfhost.md 15 KB
- reference/howto/library-management.md 1.0 KB
- reference/howto/multi-screen-prototype.md 7.4 KB
- reference/howto/single-screen.md 7.6 KB
- reference/howto/theme-setup.md 2.6 KB
- reference/howto/token-registration.md 1.2 KB
- reference/pipeline/01-token-sync.md 2.8 KB
- reference/pipeline/02-style-dictionary.md 3.5 KB
- reference/pipeline/03-storybook.md 6.2 KB
- reference/pipeline/04-vrt.md 3.6 KB
- reference/pipeline/overview.md 5.0 KB
- reference/workflow/phase-01-audit.md 2.8 KB
- reference/workflow/phase-02-wireframe.md 1.8 KB
- reference/workflow/phase-03-tokens.md 2.1 KB
- reference/workflow/phase-04-components.md 1.9 KB
- reference/workflow/phase-05-library.md 2.8 KB
- reference/workflow/phase-06-prototype.md 1.3 KB
- reference/workflow/phase-07-handoff.md 1.7 KB
- reference/workflow/phase-08-maintenance.md 1.7 KB
- scripts/mcp-proxy/docker-compose.yml 666 B
- scripts/mcp-proxy/Dockerfile 173 B
- scripts/mcp-proxy/package-lock.json 39 KB
- scripts/mcp-proxy/package.json 133 B
- scripts/mcp-proxy/proxy-server.mjs 21 KB runs code
- scripts/mcp-snippets/00-rest-api.js 9.5 KB runs code
- scripts/mcp-snippets/10-token-utils.js 17 KB runs code
- scripts/mcp-snippets/20-token-sync.js 14 KB runs code
- scripts/mcp-snippets/90-core.js 17 KB runs code
- scripts/penpot-selfhost/.env.example 4.5 KB
- scripts/penpot-selfhost/docker-compose.yml 8.6 KB
- scripts/penpot-selfhost/mcp-connect/.dockerignore 14 B
- scripts/penpot-selfhost/mcp-connect/Dockerfile 1.2 KB
- scripts/penpot-selfhost/mcp-connect/mcp-connect.mjs 38 KB runs code
- scripts/penpot-selfhost/mcp-connect/package-lock.json 1.6 KB
- scripts/penpot-selfhost/mcp-connect/package.json 126 B
- scripts/penpot-selfhost/mcp-connect/penpot-api.mjs 6.2 KB runs code
- scripts/penpot-selfhost/patches/Dockerfile.frontend-patched 1.7 KB
- scripts/penpot-selfhost/patches/entrypoint-wrapper.sh 1.2 KB runs code
- scripts/penpot-selfhost/patches/ime-fix-source.patch 13 KB
- scripts/penpot-selfhost/patches/ime-fix.js 1.1 KB runs code
- scripts/penpot-selfhost/patches/mcp-keepalive.cjs 2.6 KB runs code
- scripts/penpot-selfhost/patches/test/package-lock.json 2.1 KB
- scripts/penpot-selfhost/patches/test/package.json 130 B
- scripts/penpot-selfhost/patches/test/playwright.config.mjs 513 B runs code
- scripts/penpot-selfhost/patches/test/test-ime-fix.spec.mjs 14 KB runs code
- scripts/penpot-selfhost/penpot-manage.sh 23 KB runs code
- scripts/penpot-selfhost/penpot-mcp/Dockerfile 3.9 KB
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.
- 11d ago First seen · 229 lines · 85 tokens per session scan A b363a7953dd9
penpot is a skill published in the GitHub repository tkhr-sait/penpot-selfhost-mcp (5 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 4,557 once invoked, about $0.0004 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 2026-08-31.
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.
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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.