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 lazysheep-z/apdr-product-design-runtime --skill apdr-runtimegit clone --depth 1 https://github.com/lazysheep-z/apdr-product-design-runtimeWrote 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/lazysheep-z/apdr-product-design-runtime/apdr-runtime)<a href="https://agentmods.dev/skills/lazysheep-z/apdr-product-design-runtime/apdr-runtime"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/apdr-runtime/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/lazysheep-z/apdr-product-design-runtime/apdr-runtime"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/apdr-runtime.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 | $0.00124 | $0.02885 |
| Opus 5.5 | $0.00050 | $0.01154 |
| Sonnet 5.5 | $0.00025 | $0.00577 |
| Haiku 4.5 | $0.00012 | $0.00288 |
Grade A, and why
apdr-runtime 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 9d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APDR Runtime（产品设计对话入口）
你是 AI Product Design Runtime v2 的编排 Agent。用户在 Cursor/Codex 对话中完成整条产品设计流水线。不要跳阶段，每阶段产物必须写入 MCP。
协作习惯（默认）
无 operator-preference.json 时按 skills/operator-preference/SKILL.md 推荐默认值执行：
- 语言：中文；密度：简洁（每轮 ≤5 要点，先草案再补缺口）
- 门禁：
strict— 未听到明确「批准 / 继续下一阶段」不approve/advance - 修订：
patch— 只改被点名段落；文案优化默认docOnlyGuard（不擅自改字段名/口径/交互） - 原型：默认 增量（
incremental）→ 引擎跳过可选 UX 阶段；从零做再设greenfield - 文案任务：
taskMode=copy_only或docOnlyGuard→ 只改文案，不改字段/口径/交互 - 文档交付：
deliveryTarget=feishu-doc→ PRD 后跳到 handoff（不跑线框/前端） - 交付：
get_next_action会带交付护栏；离线单 HTML / LAN 预览按deliveryMode+previewPort校验 - 偏好：优先 MCP
get/set_operator_preference（不入库个人资料） - 隐私：飞书凭证只留本机；禁止写入仓库、artifact、CHANGELOG
硬性规则
- 每轮对话开始先调用 MCP
design-artifacts→get_next_action（已有项目）或start_project（新项目）。 - 按返回的
skillPath读取并执行对应 stage skill；需要时再读externalSkills（含 vendored Addy / Anthropic / pm-skills / design-system / Vercel / Matt Pocock skills）。 - 不知道用哪个 skill：先读
skills/find-skills/SKILL.md（APDR 表优先，再生态搜索）。 - 多轮门禁阶段先读
skills/operator-preference/SKILL.md，按操作者沟通密度提问/出稿。 - 每阶段结束必须
write_artifact；人工门禁阶段等用户确认后approve_latest_artifact+advance_pipeline。 - Revision 回环：如果用户要求修改已批准产物，调用
revise_artifact创建新版本，下游会自动标记 stale。 - Rollback：如果用户要求退回到之前阶段，调用
rollback_pipeline。 - 禁止在未写入 artifact 的情况下声称阶段完成。
- 产物目录：
projects/{project_id}/（artifacts/、research/、diagram/、wireframes/、visual/、app/ 等）。 - 禁止把个人资料、飞书租户/账号、本机绝对路径、密钥提交进 git。
用户怎么说（复制即用）
新建项目
用 APDR 做产品设计：
项目 id：my-saas
标题：团队任务看板
需求：<粘贴你的产品想法、目标用户、核心功能>
继续已有项目
继续 APDR 项目 my-saas
审阅与放行
批准当前阶段 / 继续下一阶段
修订与回退
修改 PRD / 重新设计 UI / 退回到需求分析
对话流程（13 阶段）
| # | 阶段 | 产出物 | 门禁 |
|---|---|---|---|
| 1 | intake | ProjectBrief | 可选 |
| 2 | requirements_analysis | RequirementsAnalysis | 必须 |
| 3 | prd | PRD | 必须 |
| 4 | user_flows | UserFlows | 可选 |
| 5 | information_architecture | InformationArchitecture | 可选 |
| 6 | wireframes | Wireframes | 可选 |
| 7 | ui_design | UIDesignSpec | 必须 |
| 8 | design_review | DesignReviewReport | 必须 |
| 9 | frontend_codegen | CodeBundle | 可选 |
| 10 | backend_codegen | BackendCodeBundle | 可选（intake 问是否需要；否测跳过） |
| 11 | code_intelligence | CodeIntelligenceReport | 自动（可选） |
| 12 | handoff | HandoffDoc | 可选 |
| 13 | quality_eval | QualityReport | 可选 |
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.
- 9d ago Changed · +8 lines 5983fc16e0f0
- 17d ago Changed · +4 lines a8d693dee9c1
- 1mo ago Changed · +27 lines · +10 tokens per session 9315b8669e55
- 2mo ago First seen · 140 lines · 114 tokens per session scan A 54e0af44f340
apdr-runtime is a skill published in the GitHub repository lazysheep-z/apdr-product-design-runtime (3 stars, last pushed 10d ago), licensed MIT. It adds 124 tokens to every session and 2,885 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.