agentmods.dev

design-copywriting

design-copywriting is a skill for Claude Code from modu-ai/moai-cowork. It costs 81 tokens per session (744 once invoked), scanned A, original, Apache-2.0.

A copywriting workflow for marketing and product pages that uses a brand voice and returns structured text for page sections.

In plain words
What is it for?
Use it to write or revise hero text, feature descriptions, social proof, calls to action, footers, onboarding text, empty states, and error messages.
Why use it?
It keeps headlines, calls to action, product text, and other sections consistent with the brand and easier for later tools to use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

not rated 315repo +1 changed 1mo ago A scan SkillSpector: pass 81 tokens original Apache-2.0

Good fit Use it to write or revise hero text, feature descriptions, social proof, calls to action, footers, onboarding text, empty states, and error messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/design-copywriting
View source ↗ modu-ai/moai-cowork cowork.mo.ai.kr
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 modu-ai/moai-cowork --skill design-copywriting
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

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-copywriting

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/design-copywriting"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/design-copywriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 744 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 $0.00081 $0.00744
Opus 5.5 $0.00032 $0.00298
Sonnet 5.5 $0.00016 $0.00149
Haiku 4.5 $0.00008 $0.00074

Measured 1mo ago against content hash 1468d6336b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-copywriting 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 1mo 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-copywriting/SKILL.md · 30 lines

What it actually says

브랜드 카피 작성

브랜드 보이스, 대상 사용자, 화면 목적과 실제 제품 기능을 확인해 문구를 쓴다. MoAI 프로젝트에 .moai/project/brand/brand-voice.md가 있으면 읽고 그 용어와 문체를 따른다. 데스크톱 앱에서 그 파일이 없으면 사용자가 제공한 브랜드 자료를 사용한다. 자료가 없으면 임시 문체를 제안값으로 표시하고 브랜드 확정 카피라고 부르지 않는다.

진행 방법

  1. 필요한 화면과 각 문구의 역할을 정한다. 히어로·기능·가격·후기·푸터를 모든 페이지에 강제하지 않는다.
  2. 실제로 제공하는 기능, 적용 대상, 조건과 제약을 자료에서 확인한다. 수치, 무료 체험, 환불, SLA, 고객사 이름, 후기, 경쟁 우위를 만들어내지 않는다.
  3. 제목은 사용자가 얻는 결과나 해결할 작업을 구체적으로 쓰고, 버튼은 누른 뒤 일어나는 동작을 분명히 쓴다. 오류 메시지에는 문제와 사용자가 취할 수 있는 다음 행동을 담는다.
  4. 브랜드가 쓰는 언어와 호칭을 유지한다. 상투어와 근거 없는 최상급 표현을 점검하되, 실제 브랜드 서체·표현을 일괄 금지하지 않는다.
  5. 대안 문구는 비교가 유용할 때만 만든다. 변형을 만들었다는 이유로 A/B 테스트를 수행하거나 전환율이 높다고 주장하지 않는다.
  6. 최종 문구의 사실·숫자·링크·법적 문구를 원자료와 대조한다. 미확인 항목은 공개용 문구에 넣지 않고 확인 과제로 남긴다.

산출물

MoAI 코드 기반 디자인 파이프라인이 섹션 JSON을 기대하면 page_type, sections, metadata 구조로 출력하고 실제 필요한 섹션만 포함한다. 각 섹션의 primary는 기본 문구이며 variant_a는 실제 대안이 있을 때만 쓴다. 일반 데스크톱 요청은 표나 문서처럼 사용자가 편집하기 쉬운 형식으로 낸다. 자동 계산하지 않은 읽기 수준이나 성과 점수를 메타데이터에 채우지 않는다.

카피 길이는 실제 레이아웃과 언어에 맞춰 조정한다. 영어의 단어 수나 Flesch-Kincaid 점수를 한국어 카피에 적용하지 않는다. 디자인 토큰과 레이아웃을 함께 만드는 경우 moai-designer:design-brand-system에 문구 길이와 계층을 전달한다. 문체 검수에는 moai-coworker:ai-slop-reviewer 또는 moai-writer:korean-humanize를 사용할 수 있지만 사실·의미·숫자는 보존한다.

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. 1mo ago Changed · +1 lines 1468d6336b52
  2. 1mo ago Changed · -239 lines · -55 tokens per session 7fccc5ebd7ff
  3. 2mo ago First seen · 268 lines · 136 tokens per session scan A 2eb0365ed57b

Subscribe to this mod's changes

design-copywriting is a skill published in the GitHub repository modu-ai/moai-cowork (315 stars, last pushed 29d ago), licensed Apache-2.0. It adds 81 tokens to every session and 744 once invoked, about $0.0003 per session on Opus 5.5. 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.

Claude Codeai-agentsanthropicclaude-pluginsmarketplaceplugin-marketplace
Related

design-copywriting compared with skills from other repositories

design-copywriting next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
design-copywritingmodu-ai/moai-coworkSkill31529d agoApache-2.0A81Claude Code
phpunit-unit-test-reviewingshopwareLabs/ai-coding-toolsSkill4510d agoMITA31Claude Code
linkedin-writer-vaultnaveedharri/benai-skillsSkill7828d agoMITA153Claude Code
operatornaveedharri/benai-skillsSkill7828d agoMITA156Claude Code
crm-prospect-miningnaveedharri/benai-skillsSkill7828d agoMITA222Claude Code
bens-voicenaveedharri/benai-skillsSkill7828d agoMITA109Claude Code
ads-competitornaveedharri/benai-skillsSkill7828d agoMITA74Claude Code