design-sync-upload

design-sync-upload is a skill for Claude Code from modu-ai/moai-cowork. It costs 211 tokens per session (6,496 once invoked), scanned A, original, Apache-2.0.

An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.

In plain words
What is it for?
Use it to register brand assets and design tokens with Claude Design, or create an upload guide and staged asset folder for someone to upload manually.
Why use it?
It removes the need to upload scattered design files one by one and provides a manual path when the connection is unavailable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./design-sync-staging/.

Part of the moai-designer plugin — 17 skills shipped together

Good fit Use it to register brand assets and design tokens with Claude Design, or create an upload guide and staged asset folder for someone to upload manually.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork
agentmods
npx agentmods add skills/modu-ai/moai-cowork/design-sync-upload

Made for: Claude Code.

Or install moai-designer, the plugin that ships this one along with the rest of its 17 skills.

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 design-sync-upload

README.md
[![agentmods](https://agentmods.dev/badge/skills/modu-ai/moai-cowork/design-sync-upload/github.svg)](https://agentmods.dev/skills/modu-ai/moai-cowork/design-sync-upload)
Your own site
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/design-sync-upload"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/design-sync-upload/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 design-sync-upload

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/design-sync-upload"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/design-sync-upload.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00211 $0.06496
Opus 5 $0.00105 $0.03248
Sonnet 5 $0.00042 $0.01299
Haiku 4.5 $0.00021 $0.00650

Measured 6d ago against content hash a70f10d1bb14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

design-sync-upload 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 6d 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.

plugins/moai-designer/skills/design-sync-upload/SKILL.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

design-sync-upload — Claude Design 업로드 (자동 + 수동 폴백)

개요

디자인 시스템 자산을 Claude Design에 올리는 방식은 환경에 따라 두 가지입니다. 이 스킬은 자동(DesignSync MCP)을 먼저 시도하고, 인증·가용성 조건이 안 되면 **수동 폴백(UPLOAD-GUIDE.md + 스테이징 폴더)**으로 자연스럽게 강등합니다. 어느 경로든 사용자가 손으로 파일을 흩뿌리지 않고 한 번에 업로드할 수 있게 만드는 것이 목표입니다.

이 SKILL.md는 인증 감지·자동(DesignSync MCP) 경로·수동 폴백·사용 예시를 모두 포함합니다. DesignSync는 method로 디스패치하는 단일 MCP 도구이며(파라미터 상세는 §자동 경로 참조), 미인증·미가용 시 조용히 수동 폴백으로 강등합니다.

트리거 키워드

Claude Design 업로드, DesignSync MCP, design-login, 디자인 시스템 동기화, UPLOAD-GUIDE, 자산 스테이징, write_files, register_assets

입력

입력 형태
DESIGN.md design-system-prep 산출물
토큰 design-tokens-transformer 산출물(DTCG/CSS/shadcn)
자산 로고 변형(가로/정사각/마스코트/WH), 폰트, 이미지

경로 선택 — 인증 감지 분기

자산 준비
  → [감지] DesignSync MCP 가용 AND /design-login 인증됨?
      ├─ YES → 자동 경로 (DesignSync MCP)
      └─ NO  → 수동 폴백 (UPLOAD-GUIDE.md + 스테이징 폴더)

감지 신호

신호 확인 방법 판정
DesignSync MCP 도구 존재 현재 세션 도구 목록에 DesignSync가 로드됐는지 없음 → 즉시 수동
/design-login 인증됨 무해한 read 메서드(list_projects) 호출 시 인증 에러 미발생 정상 반환 → 자동 가능
미인증 에러 시그니처 관측된 문자열: DesignSync needs design-system authorization. Run /design-login to authorize it with your claude.ai account 이 문자열 감지 → 미인증 확정 → 수동

감지 순서(부작용 최소화): ① 도구 존재만 사전 확인 → ② 무해한 read 메서드(list_projects/get_project)로 인증 상태 판별(쓰기 없음) → ③ 여기서 미인증 에러가 나오면 폴백. 쓰기 메서드로 인증을 떠보지 않는다(부분 업로드 위험).

감지 실패 시 기본 강등 정책: 감지 자체가 모호하면(도구는 있으나 인증 상태 불명, read 호출이 애매한 에러 반환 등) 수동 폴백을 기본값으로 강등한다. 인증됨을 관측 없이 가정하고 자동을 강행하면 부분·중복 업로드 위험이 있으므로, 애매하면 항상 수동이다(미관측 상태를 성공으로 가정 금지).

자동 경로 — DesignSync MCP

/design-login 인증 상태에서 DesignSync MCP 도구로 자산을 직접 등록합니다.

DesignSync는 method로 디스패치하는 단일 도구다. 순서 의존성이 강제된다: read → finalize_plan → write. finalize_plan이 먼저 경로 집합을 잠근 뒤에야 write가 허용된다(플랜 밖 경로/planId 없는 write는 거부).

  1. read (list_projects/get_project/list_files/get_file) — 대상 프로젝트 확인(쓰기 가능 + type: PROJECT_TYPE_DESIGN_SYSTEM) 후 원격 구조로 컴포넌트 단위 diff 구성. 전량 교체가 아니라 증분.
  2. 승인 게이트 — finalize_plan 호출 전. 아래 §쓰기·삭제 승인 게이트. finalize_plan이 띄우는 런타임 권한 프롬프트가 이 게이트를 대신하지 못한다 — 그 프롬프트는 경로만 보여주고 그 경로에 무엇이 들어가는지는 보여주지 않는다.
  3. finalize_plan — 승인된 경로 집합(writes/deletes, 글롭 허용)과 읽기 소스 디렉토리(localDir)를 확정 → planId 반환. 권한 프롬프트 발생.
  4. write_files (+ delete_files) — planId로 파일 업로드. 각 파일은 localPath(디스크에서 직접 읽어 업로드 — 내용이 컨텍스트에 유입되지 않음, 권장) 또는 소량 인라인 data. 콜당 최대 256개(초과 시 같은 planId로 분할).
  5. register_assets (레거시) — Design System 카드는 이제 preview HTML 첫 줄 <!-- @dsCard group="…" --> 마커에서 자동 인덱싱(앱이 _ds_manifest.json으로 컴파일)되므로 명시 등록 불필요. @dsCard 마커가 없는 수기 프로젝트에서만 사용.

Read the full file on GitHub · 330 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. 6d ago First seen · 330 lines · 211 tokens per session scan A a70f10d1bb14

Subscribe to this mod's changes

design-sync-upload is a skill published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 7d ago), licensed Apache-2.0. It adds 211 tokens to every session and 6,496 once invoked, about $0.0011 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 2026-09-03.

Related

Other skills, from other repositories

excalidraw

Create visual presentations, slide decks, and explanatory diagrams in Excalidraw. Use when user asks to create a presentation, slide deck, visual explainer, pitch deck, comparison diagram, process flow, or any multi-slide visual content. Supports two output modes — generating .excalidraw JSON files OR injecting slides…

naveedharri/benai-skills · 99 tokens

infographic-old

Basic infographic generator. Just tell me what you want and I'll make it.

naveedharri/benai-skills · 19 tokens

carousel-builder

Build a Ben AI image-first carousel (Type B) from provided source content and export it as a PDF. Give it a newsletter, a YouTube transcript, a LinkedIn post, or a raw brief; it picks the slide count (3-10), writes the copy in Ben's voice, renders every slide with Higgsfield GPT Image 2, composites the real-logo brand…

naveedharri/benai-skills · 132 tokens

design-system-creator

Produces a complete, Claude-Design-compatible design system folder for any brand, ready to upload to Claude Design's "Set up your design system" flow and use across every future asset (websites, landing pages, pitch decks, Instagram/LinkedIn carousels, infographics, emails, ads). Handles two paths: building a brand…

naveedharri/benai-skills · 210 tokens

instant-ui

Build a BenAI-branded HTML page in the neo-brutalist instant-ui design language (cream background, near-black ink, 3px hard borders, 6px zero-blur shadows, a blue/green/amber gradient stripe, system font plus SF Mono, weight-900 headings). Use for any BenAI landing page, offer, sales, or pricing page, onboarding or…

naveedharri/benai-skills · 217 tokens

infographic

Generate professional infographics using Nano Banana MCP (Gemini AI image generation). Follows a guided flow — analyze content, suggest visualizable concepts, propose visualization approaches, then generate on-brand images. USE THIS SKILL WHEN user says "create infographic", "make a visual", "design an infographic"…

naveedharri/benai-skills · 172 tokens