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 agentmods add skills/reddishz/designdoc/design-docnpx skills add reddishz/designdoc --skill design-docgit clone --depth 1 https://github.com/reddishz/designdocWrote 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/reddishz/designdoc/design-doc)<a href="https://agentmods.dev/skills/reddishz/designdoc/design-doc"><img src="https://agentmods.dev/badge/skills/reddishz/designdoc/design-doc.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.06137 |
| Opus 5 | $0.00044 | $0.03069 |
| Sonnet 5 | $0.00017 | $0.01227 |
| Haiku 4.5 | $0.00009 | $0.00614 |
Grade A, and why
design-doc 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.
How it starts
The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品设计文档规范（UED）
AI 运行时配置解析规则
AI 在创建或编辑设计文档时，模板中的 {当前用户.作者} 与 {项目编码} 按当前作用域的 README.md 解析；额外配置文件 已移除且 MUST NOT 继续创建或使用。
作用域判定规则：
- 单应用模式：若业务文档直接位于
ued/下，则ued/README.md同时承担入口、项目元信息、编码模式、编码计数器与全局索引。 - 多应用模式：若存在多个应用，则每个应用 MUST 位于
ued/{app-name}/子目录下。 - 多应用顶层 README：
ued/README.md仅承担多应用总入口、应用注册表、公共规则与跨应用导航，MUST NOT 作为某个具体应用的项目编码来源。 - 多应用应用级 README：
ued/{app-name}/README.md承担该应用的项目元信息、编码模式、编码计数器、文档导航与应用级全局索引。
获取优先级（高到低）：
作者字段：
- 当前作用域
README.md中的项目元信息字段（如author/maintainer） - 运行环境可识别的当前执行主体标识（如工具可获取）
- 默认值：
产品架构组
项目编码字段（高级扩展用法）：
- 当前作用域
README.md中的项目元信息字段project_code - 顶层
ued/README.md的应用注册表中，与目标应用目录匹配的project_code（仅多应用模式下辅助校验） - 默认值：无（即禁用项目编码前缀，采用简洁编码格式）
启用规则：AI MUST NOT 启用项目编码前缀，除非已显式配置且请求发起方明确确认。默认情况下，一律采用简洁编码格式（如 FR-001）。
提示规则（新增强制约束）：
- 当 AI 识别到
ued/下存在多个应用或多个独立业务域的设计文档时，MUST 提示将应用迁移到ued/{app-name}/子目录，并在顶层ued/README.md注册应用编码，同时在应用级README.md中定义project_code。 - 当 AI 识别到当前仓库已存在某一应用的设计文档，而当前任务是在此基础上新增另一应用的设计文档时，MUST 在创建前提示采用多应用模式，并为新应用补齐子目录
README.md与顶层应用注册表。 - 若尚未配置
project_code，AI MUST 先提示补充配置，再进入编码分配阶段；未获确认前，MUST NOT 擅自启用前缀。 - 上述提示的目标是确保多个应用并存时，编码、索引、引用与废弃追溯仍可保持全局唯一且语义清晰。
若作用域 README.md 不存在或未声明相应字段，首次使用时直接采用默认值继续工作：
author = 产品架构组project_code = (空)
随后 AI SHOULD 提醒补充或编辑对应作用域的 README.md 元信息区块，特别是当检测到目录中存在多个应用或新增独立应用迹象时。
项目编码规则（高级模式下）：
- 长度：2-4位大写字母
- 只能包含字母 A-Z
- 有效示例：
CRM、ERP、CMS、COM、HRS
README 元信息最小字段（RECOMMENDED）：
project_nameproject_codedoc_mode：single-app或multi-appscopeauthor/maintainer
入口介绍
本 skill 的目标不是向人类解释如何写文档，而是约束 AI 的执行方式，确保 AI 在设计文档生成、修改、审查、编码管理和废弃处理时遵循统一意图、统一流程与统一停顿点。
详细规范请参考 references/ 目录下的专项文档：
- 编码体系：references/coding-system.md
- 层级体系：references/layer-system.md
- 术语与概念：references/glossary-conventions.md
- 状态定义：references/status-definitions.md
- 废弃处理：references/deprecation-guide.md（细项废弃）
- 废弃文档处理：references/deprecated-docs-guide.md（文档废弃）
- 审核指南：references/review-guidelines.md
- 项目 AGENTS.md 指南：references/project-agents-guide.md
- 文档模板：assets/templates/
What ships with it
25 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.
- assets/guides/flowchart-guide.md 4.9 KB
- assets/templates/adr.md 2.4 KB
- assets/templates/index.md 4.2 KB
- assets/templates/l0-roadmap.md 4.4 KB
- assets/templates/l0-strategy.md 3.1 KB
- assets/templates/l1-stakeholder.md 3.4 KB
- assets/templates/l2-requirements.md 4.4 KB
- assets/templates/l3-concept-architecture.md 4.3 KB
- assets/templates/l4-system-design.md 3.8 KB
- assets/templates/l5-detailed-design.md 4.1 KB
- assets/templates/l6-verification.md 4.1 KB
- assets/templates/planning.md 5.5 KB
- assets/templates/project-registry.md 1.9 KB
- assets/templates/readme-template.md 7.3 KB
- assets/templates/ref.md 3.1 KB
- references/coding-system.md 24 KB
- references/deprecated-docs-guide.md 25 KB
- references/deprecation-guide.md 10 KB
- references/glossary-conventions.md 3.3 KB
- references/layer-system.md 5.0 KB
- references/project-agents-guide.md 3.0 KB
- references/README.md 1.2 KB
- references/review-guidelines.md 20 KB
- references/status-definitions.md 6.1 KB
- scripts/check_docs.py 13 KB runs code
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.
- 6d ago First seen · 376 lines · 87 tokens per session scan A 7d7853d9d005
design-doc is a skill published in the GitHub repository reddishz/designdoc (11 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 6,137 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 2026-08-30.
Other skills, from other repositories
openprd-frontend-design
为 OpenPrd 的界面、页面、视觉、样式和前端体验任务提供设计资产框架、审美立意、反 AI 味门禁和实现前方向评审规则。.
blueprint-standards
Defines structural design artifact formats — information architecture, user flows, content model, brand direction, Visual Tokens, and AI interaction model. Use when creating or reviewing design artifacts that precede prototype generation.
html-demo
仿真型 HTML 交互 demo 生成：按用户截图复刻真实界面，产出自包含、全状态可达（带模拟开关）的可交互单文件 demo，落 tmp/ 就地多轮迭代；拍板后归档 prototypes/ 并衔接 prd-writer「demo 先行变体」写 PRD。.
design-perspective
Integrates design principles, WCAG 2.2 AA accessibility, persona context, and state design into product decisions. Use when reviewing UX decisions, checking accessibility, applying design principles, or ensuring state coverage in acceptance criteria.
recipe-blueprint
Selects and defines the structural design context needed by a prototype or PRD. Use when shared information architecture, flows, content, brand, Visual Tokens, or AI interaction decisions are missing.
recipe-persona
Creates or updates evidence-backed personas with the context and JTBD needed for product decisions. Use when user segments or behavior affect discovery, design, or requirements.