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.
git clone --depth 1 https://github.com/reddishz/designdocnpx agentmods add skills/reddishz/designdoc/design-docWrote 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/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/reddishz/designdoc/design-doc"><img src="https://agentmods.dev/badge/skills/reddishz/designdoc/design-doc.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 | $0.00091 | $0.02085 |
| Opus 5.5 | $0.00036 | $0.00834 |
| Sonnet 5.5 | $0.00018 | $0.00417 |
| Haiku 4.5 | $0.00009 | $0.00209 |
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 5d 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 — 125 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）
本 skill 约束 AI 的执行方式，不是人类写作教程。规则与流程在 references/；本文是运行时路由：选对 workflow、守住不变量、该停则停。
措辞强度见 coding-system.md · 需求级别说明。
一致性（无冲突）
包内与 ued/ 内同一规则只允许一种表述。发现技能包两处不一致、或设计文档之间/与基线冲突 → 视为规范缺陷，当轮修正或列入人审后修正；MUST NOT 用「优先级表」掩盖冲突。定稿与发布前审查须确认无未解消冲突。
运行时步骤
- 确认作用域存在
ued/（或应用级设计树）；解析配置见 runtime-config.md。 - 按下方任务路由加载对应 workflow（MUST read）；仅在流程分支需要时再打开所列 rule。
- 解冻、废弃、批量编码或动基线前：先短计划，人审停点见各 workflow 的 Checkpoint。
- 改完跑
check_docs.py；通过≠语义正确。 - 仅当本轮改过
ued/、要定稿/提交、或有基线漂移须询问时，再加载 lifecycle.md 走 Checkpoint 5；未改设计文档则不必读 lifecycle。
任务路由
| 意图 | MUST 先读 |
|---|---|
| 增量加功能 / 加需求 | change-feature.md |
| 创建新设计文档 | create-document.md |
| 分配编码；改 ID/类型码/正式标题或含义 | allocate-and-lock.md |
| 废弃细项/文档 | lifecycle.md（作废段） |
| 定稿确认 / 提交收尾 / 基线漂移询问 | lifecycle.md（Checkpoint 5；见上「仅当」） |
| 基线 PATCH / MINOR / MAJOR | baseline-change.md |
| 写/改 EVAL | eval-report-profile.md + 模板 eval.md |
| 审查设计文档 | review-guidelines.md |
改功能 / 修缺陷 / 改行为（有 ued/） |
before-code-change.md（先判定设计要不要改） |
| 按已定设计实现代码 | implement-from-design.md |
动代码相关意图：MUST 先走 before-code-change，MUST NOT 默认先改业务代码。
不变量（任何任务）
- 已分配编码 MUST NOT 删除或复用；放弃走作废。
- 编码 ID/类型码永不就地改；
正式/草案标题与已正式业务含义不就地改（通道见 锁定矩阵）。 - 未入当前产品基线（或基线 revision 落后）的内容 MUST NOT 作为实现依据。
- 语义引用只用细项/文档编码，MUST NOT 用章节编号；跨文件路径以
./或../开头。 ued/MUST NOT 含可执行实现代码（算法/契约/状态机可以）。- 高风险生命周期与基线动作 MUST 经人确认（Checkpoint）；AI MUST NOT 自行定稿或
--bump-product。 - 模板即复制源；哨兵外说明 MUST NOT 写入实例（模板边界）。
What ships with it
60 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 6.6 KB
- assets/templates/adr.md 3.1 KB
- assets/templates/eval.md 6.0 KB
- assets/templates/index.md 12 KB
- assets/templates/l0-roadmap.md 4.0 KB
- assets/templates/l0-strategy.md 4.4 KB
- assets/templates/l1-stakeholder.md 4.1 KB
- assets/templates/l2-requirements.md 8.7 KB
- assets/templates/l3-concept-architecture.md 5.4 KB
- assets/templates/l4-system-design.md 5.2 KB
- assets/templates/l5-detailed-design.md 4.9 KB
- assets/templates/l6-verification.md 5.7 KB
- assets/templates/planning.md 6.2 KB
- assets/templates/project-registry.md 1.7 KB
- assets/templates/readme-template.md 7.0 KB
- assets/templates/ref.md 3.4 KB
- references/coding-system.md 46 KB
- references/doc-deprecation.md 16 KB
- references/eval-report-profile.md 4.9 KB
- references/glossary-conventions.md 3.3 KB
- references/item-deprecation.md 15 KB
- references/layer-system.md 9.8 KB
- references/object-model.md 12 KB
- references/product-version.md 9.7 KB
- references/project-agents-guide.md 3.7 KB
- references/README.md 2.5 KB
- references/review-guidelines.md 28 KB
- references/status-definitions.md 30 KB
- references/type-profiles.md 24 KB
- references/workflows/allocate-and-lock.md 2.0 KB
- references/workflows/baseline-change.md 657 B
- references/workflows/before-code-change.md 1.7 KB
- references/workflows/change-feature.md 1.1 KB
- references/workflows/create-document.md 1.0 KB
- references/workflows/implement-from-design.md 1.3 KB
- references/workflows/lifecycle.md 3.1 KB
- references/workflows/runtime-config.md 1.4 KB
- scripts/baseline_ops.py 13 KB runs code
- scripts/check_docs.py 190 KB runs code
- scripts/tests/fixtures/baselines/v1.0.yaml 456 B
- scripts/tests/fixtures/EVAL-901-ok.md 2.4 KB
- scripts/tests/fixtures/EVAL-902-no-scope.md 1.8 KB
- scripts/tests/fixtures/EVAL-903-bad-meta.md 1.7 KB
- scripts/tests/fixtures/EVAL-904-preamble-leak.md 2.5 KB
- scripts/tests/fixtures/L2-901-ok-full.md 667 B
- scripts/tests/fixtures/L2-902-no-status.md 459 B
- scripts/tests/fixtures/L2-903-status-not-first.md 493 B
- scripts/tests/fixtures/L2-904-gov-order.md 486 B
- scripts/tests/fixtures/L2-905-gov-missing.md 392 B
- scripts/tests/fixtures/L2-906-gov-badval.md 488 B
- scripts/tests/fixtures/L2-907-trace-mid.md 566 B
- scripts/tests/fixtures/L2-908-trace-order.md 596 B
- scripts/tests/fixtures/L2-909-src-nolink.md 530 B
- scripts/tests/fixtures/L2-910-origin-link.md 553 B
- scripts/tests/fixtures/L2-911-pln-landed-norecord.md 651 B
- scripts/tests/fixtures/L2-912-pln-nofield.md 619 B
- scripts/tests/fixtures/L2-913-pln-badval.md 655 B
- scripts/tests/fixtures/L2-914-pln-ok-landed.md 717 B
- scripts/tests/fixtures/L2-915-gate-draft-item.md 492 B
- scripts/tests/fixtures/L2-916-gate-new-item.md 490 B
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.
- 5d ago Changed · -160 lines · -14 tokens per session 97934a451fba
- 8d ago Changed · +7 lines 5c4dcfeae99e
- 9d ago Changed · +1 lines de16795affb0
- 10d ago Changed · +1 lines 948b54fe9e72
- 13d ago Changed · +41 lines · +18 tokens per session 7bbd235d907d
- 14d ago Changed · +11 lines 9cc72389efd9
- 1mo ago Changed 0ad03d3c2e9c
- 1mo ago Changed 9a8b0efd576e
- 1mo ago Changed · -253 lines c8abde7004c4
- 1mo ago First seen · 477 lines · 87 tokens per session scan A 6392ffa65e17
design-doc is a skill published in the GitHub repository reddishz/designdoc (14 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 2,085 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
openprd-frontend-design
A design guide for OpenPrd interface and frontend work. It helps define the page's purpose, visual direction, assets, layout, and quality checks before implementation.
html-demo
A workflow for building a self-contained interactive HTML demo from a screenshot and a short requirement. The demo imitates the interface and includes simulated controls so its states can be explored.
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.
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.