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.
npx skills add shihchengwei-lab/separation-and-audit-claude-code --skill design-integrity-guardgit clone --depth 1 https://github.com/shihchengwei-lab/separation-and-audit-claude-codeWrote 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/shihchengwei-lab/separation-and-audit-claude-code/design-integrity-guard)<a href="https://agentmods.dev/skills/shihchengwei-lab/separation-and-audit-claude-code/design-integrity-guard"><img src="https://agentmods.dev/badge/skills/shihchengwei-lab/separation-and-audit-claude-code/design-integrity-guard/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/shihchengwei-lab/separation-and-audit-claude-code/design-integrity-guard"><img src="https://agentmods.dev/badge/skills/shihchengwei-lab/separation-and-audit-claude-code/design-integrity-guard.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 | $0.00111 | $0.01072 |
| Opus 5 | $0.00056 | $0.00536 |
| Sonnet 5 | $0.00022 | $0.00214 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
design-integrity-guard 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 12d 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.
What it actually says
Design Integrity Guard
觸發條件
任何涉及用戶/玩家可見文字的任務：文案撰寫、UI 文字、系統訊息、錯誤提示、引導文字、故事內容、通知文案、商店文案。
啟動步驟
- 讀取
docs/design-principles.md（若未在 context 中） - 確認當前任務的內容類型
- 載入對應的判準區塊
共通判準（所有內容類型適用）
語氣底色
從 design-principles.md 的「用戶應該感受到什麼」提取。
一句話判準：讀你的 design-principles.md「最終判準」欄位，每段文字都必須通過。
禁用詞彙
從 design-principles.md 的「禁用詞彙」提取。
反模式
從 design-principles.md 的「絕對不能變成什麼」提取。任何產出如果讓產品更接近這些反模式，退回重寫。
各內容類型判準
以下為模板。請根據你的產品替換範例內容。
引導/開場文字
- 不做功能導覽、不解釋系統
- 讓用戶先體驗、先感受，再理解
- 語氣像產品在等你，不是教學在教你
- 自訂：___
角色/物件介紹
- 不寫功能標籤、不寫能力數值
- 寫的是這個角色/物件的「氣質」
- 讀起來讓人想認識，不是想比較
- 自訂：___
對話/互動文字
- 關係深化的方向是___（例：越安靜越有重量 / 越熟越隨性）
- 禁止的方向是___（例：越來越撒嬌 / 越來越像客服）
- 自訂：___
UI 文字
- 按鈕用動作而非狀態（「前往」而非「確認前往」）
- 系統提示用產品世界的語言，不用系統語言
- 不用驚嘆號
- 自訂：___
通知/推播文字
- 變化要「被發現」而不是「被公告」
- 不刺激、不催促
- 自訂：___
商店/付費文字
- 不推銷、不製造焦慮
- 付費體驗讓用戶感到___，而非「在買東西」
- 自訂：___
交付前自檢
每段用戶可見文字交付前逐條檢查：
- 有沒有用到禁用詞彙？
- 讀起來像系統通知還是像產品世界在說話？
- 有沒有不自覺地寫成促銷/遊戲化/客服語氣？
- 有沒有違反 design-principles.md 的任何生死線？
- 最終判準：如果這段文字被截圖傳出去，會不會讓人覺得「這就是又一個 ___（你最不想被歸類的東西）」？
第 5 條過不了就退回重寫。
守衛模式（審查其他 agent 產出）
被 PM 派工審查時：
- 載入此 skill
- 逐段檢查產出物中的用戶可見文字
- 比對禁用詞彙
- 比對反模式
- 通過 → 回報 PM
- 不通過 → 標註具體問題 + 引用違反的判準條目 → 退回修改
標註格式：
🚫 [文字段落] — 違反：[判準條目] — 建議方向：[一句話]
What ships with it
1 file 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.
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.
- 12d ago First seen · 104 lines · 111 tokens per session scan A 356df6898694
design-integrity-guard is a skill published in the GitHub repository shihchengwei-lab/separation-and-audit-claude-code (2 stars, last pushed 4mo ago), licensed MIT. It adds 111 tokens to every session and 1,072 once invoked, about $0.0006 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
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…
ai-instruction-detox
A review and cleanup method for instructions stored in files such as CLAUDE.md, AGENTS.md, skills, context, and memory.
normies
Use when you want to see a site through fresh eyes — how different types of people experience it for the first time. Dispatches agents with varying tech sophistication who land on the site cold and report confusion, friction, and first impressions.
well-actually
Use when you want pedantic, nitpicky, opinionated feedback on a site or project — the kind of feedback you'd get from Hacker News commenters, typography snobs, grammar pedants, and standards purists. Finds the things that professional reviewers skip because they're "too minor.".
frontend-audit
ProductionOS frontend quality scanner. Auto-activates when editing React/Vue/Svelte components, CSS, or layout files. Checks accessibility, responsive design, performance, and design system consistency.
oma-design
AI design specialist skill with DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance. Covers typography, color systems, motion design (motion/react, GSAP, Three.js), responsive-first layouts, and accessibility (WCAG 2.2).