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 yunshu0909/yunshu_skillshub --skill backend-logic-designgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/backend-logic-design)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/backend-logic-design"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/backend-logic-design/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/yunshu0909/yunshu_skillshub/backend-logic-design"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/backend-logic-design.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 | $0.00329 | $0.05473 |
| Opus 5.5 | $0.00132 | $0.02189 |
| Sonnet 5.5 | $0.00066 | $0.01095 |
| Haiku 4.5 | $0.00033 | $0.00547 |
Grade A, and why
backend-logic-design 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 18d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
后端逻辑设计：把看不见的部分讲清楚
用户是产品经理，你是懂技术的搭档。前端设计回答「用户看到什么、点了会怎样」；本 skill 回答「背后发生什么、出了意外怎么办」。产出是一个后端逻辑包：一份带编号、带状态的规则表（开发、PRD、测试、审核的追溯键）+ 完整档时一页给用户看的读者版 + 审核留档。
元原则
- 每条规则都带一个案例。 规则给机器，案例给人。没有案例的规则，用户读不懂，审核也抓不到歧义（用户原话：「规则也带上案例吧 要么我看的费劲」）。
- 新的选择题一律带「时间线式」案例。 先讲具体故事（谁、什么时候、做了什么），再用表列每个选项下「发生什么 / 你看到什么 / 代价」，最后给推荐和一句理由（用户原话：「没有案例 我也不知道你要干嘛」）。
- 给用户看的按「用户会问的问题」分组，不按系统结构。 每张卡只有一个问题、一句答案、一串小例子；长表进附录（用户原话：「读起来实在是累」）。
- 用户亲口定过的不再问，没拍过板的不能当已定，AI 能定的不去问。 用户原话或签收过的设计 → 继承；计划 / 方案里写了、或 AI 上一轮自己定的 → 「你没拍过板」，要给用户过目；技术细节 AI 定、一行通知——但技术改动一旦改变用户能感知的东西（默认值、存放位置、留存、等待时间、把真的换成假的），就转成要问的题（用户 10-06：「需要人确认就找人确认」）。
- 最绕的那块逻辑做一个能点的模拟器。 模拟器还能暴露你对用户决定的误解（本 skill 的来历里，用户在模拟器上发现「最多 3 个」被理解成「平时只派 1 个」）。
- 例子优先用真实的。 用户本机真实的名字、真实发生过的事故；新功能没有真实事件时可以构造，但要标「构造」。
- 不推翻用户已定的事。 审核者的建议和已定决定冲突时，摆出来、说清代价，默认保留，问一句要不要改。
- 编号稳定、双向对照。 规则用
后-NN，给用户看过就不重排，作废的标作废不复用。每条规则写它落在哪个「用户触点」：有界面时是前端状态编号（A1、C7、F12），没界面时是T1…（验收页某一栏、停下时发的消息、命令行输出），确实没有触点写「无：理由」。前端每个状态也都要能找到背后的规则。 - 先读代码事实，再写规则。 写到现有实现的地方，在附录标出文件和行号；新建功能写明「无现存代码」，不伪造依据。事实分三种标：现状 / 目标 / 待验证。
先判断：用不用、用多深
| 档 | 什么时候 | 做哪几步 | 产出 |
|---|---|---|---|
| 完整包 | 还有没定的、用户能感知的规则，并且涉及以下任一：跨模块的数据归属、规则互相影响、同步 / 调度、升级迁移、出错降级、多步写文件 | 第 0–6 步全做 | 规则 md + 读者版 HTML（卡片、模拟器）+ 业务题页 + 边界审查留档 |
| 只出规则表 | 规则清楚、只有少量互相独立的变化（如「什么时候改写某个文件」） | 第 0、1 步；有新选择题、或有要过目的规则（proposed、新增的用户可感知规则）就做第 2 步；边界审查并进开发流程的开工前检查 |
规则 md（build.py 不放 cards.json 即可） |
| 跳过 | 用户能感知的行为不变的技术修复（拆代码、提速但结果不变） | — | 无；高风险技术问题照常走开发流程的审核 |
判断看「有没有待定的业务规则、规则之间会不会互相影响、出错后果」，不看代码量，而且只看本次改动新增或改变的部分——功能里早就有的迁移、降级分支不算。拿不准时先按「只出规则表」做，写的过程中发现规则互相牵扯再升档并告诉用户。项目约定「设计相关要先问用户走哪条流程」的，照项目约定。
- 业务都定了、但有高风险的多步写 / 崩溃恢复：按「只出规则表」，但步骤表和边界审查必做，需要时可以加一个模拟器给自己和审核者用。
- 只出规则表时，题和审查放哪：新选择题——单独用写一份
业务题.md；dev 简版里并进1-plan.md的「规则」一节（测试清单直接引用后-NN，不把同一件事写两遍）；dev 正式版里并进业务确认。边界审查——单独用自己请另一家；dev 流程里随开工前检查一起送审。
确认分工
| 产出 | 用户确认 | 另一家模型校核 | AI 自己定 |
|---|---|---|---|
| 新的选择题 | 要：用户选 | 题多、互相影响时查漏问 | 写案例、选项、推荐 |
已定过且没变的决定（status inherited：用户原话或签收过的设计） |
不再问 | 查转述有没有走样 | 整理、写出处 |
方案里写了、你没拍过板的（status proposed） |
要过目：随读者版或业务确认一起看 | 查有没有藏着改变你能感知的东西 | 标出来源，不当已定 |
| 新增的、用户能感知的规则 | 要：随读者版或业务确认一起看 | 整包一起查 | 起草 |
技术规则（status ai）：落实已定语义的保护（原子写、锁、校验、幂等） |
不用 | 高风险、跨模块的查 | 是，一行通知 |
| 技术改动改变了你能感知的东西（默认值、存放位置、留存、花钱、授权、数据删留、多等待、把真的换成假的） | 要：转成选择题 | 查 | 写案例和推荐 |
| 模拟器 | 只看演示结果 | 逻辑复杂时查 | 实现，并用列出的输入 / 预期验证 |
| 排版、生成文件、编号格式 | 不用 | 不用（浪费） | 程序检查（build.py） |
| 审核后的实质修改 | 改了行为或范围时要 | 原审核者复核受影响的规则 | 技术修复；错别字不复审 |
What ships with it
12 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/template.html 6.5 KB
- examples/审核配置/cards.json 8.9 KB
- examples/审核配置/rules.json 33 KB
- examples/审核配置/sim-挑模型.html 3.7 KB
- examples/审核配置/后端规则-审核配置.md 30 KB
- examples/审核配置/后端逻辑-审核配置.html 49 KB
- references/业务题模板.md 1.1 KB
- references/回流模板.md 1.3 KB
- references/模拟器写法.md 2.2 KB
- references/规则写法.md 6.8 KB
- references/边界清单.md 5.3 KB
- scripts/build.py 25 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.
- 18d ago First seen · 147 lines · 329 tokens per session scan A 351704a63ab4
backend-logic-design is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (784 stars, last pushed 13d ago), licensed MIT. It adds 329 tokens to every session and 5,473 once invoked, about $0.0013 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 2026-10-07.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dev-runtime
How the Node side of a dev stack runs without haven, and the backend host: pnpm dev (UI built once, backend reloading), pnpm dev:hmr (adds the Vite ui lane), tools/dev-runtime (api + worker in one Node process), backend reload on a file change, the debounce (quiet window + max wait), ports derived from PORT. Use when…
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…