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.
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote 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/rules/tashangkd/tashan-cursor-skills/skill-design-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/skill-design-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/skill-design-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/rules/tashangkd/tashan-cursor-skills/skill-design-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/skill-design-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 | $0.00168 | $0.01369 |
| Opus 5 | $0.00084 | $0.00685 |
| Sonnet 5 | $0.00034 | $0.00274 |
| Haiku 4.5 | $0.00017 | $0.00137 |
Grade A, and why
skill-design-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 10d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill/Rule/Agent 体系设计统一守门（skill-design-guard）
根因：
Skill体系设计原则_v1.0.md有完整的三型决策树（§2.5），但连接机制依赖各 Skill 自行添加 D0 行，有系统性漏洞——遗漏了 D0 的 Skill 设计类任务看不到三型框架（如 role-Skill产品经理 v1.0 只知道建 Skill，不知道可以建 Rule/Agent）。本规则将「先读原则文档」从 Skill 内部约定升级为体系级强制守门，对所有 Skill/Rule/Agent 设计类任务统一生效。
触发条件
以下任一场景触发本规则：
- 准备新建、修改、完善任何
.cursor/skills/、.cursor/rules/、.cursor/agents/中的文件 - 用户描述的任务含「Skill/Rule/Agent 设计/修改/完善/评审/优化」类语义
- 触发了
skill-designer、skill-rule-修改规范、role-Skill产品经理任一 Skill
强制前置步骤（触发后立即执行，不可跳过）
在进入任何 Skill/Rule/Agent 设计类操作前，必须先确认已读取：
Read: _内部总控/认知结构/L1_系统性文档/系统架构思维维度/Skill体系设计原则_v1.0.md
重点章节：
§2.5 三型统一决策树（Rule / Agent / Skill 的选型判断）
§4.3.5 认知根原则（每个组件的工作对应哪个 L1/L1.5 文档）
§2.2 Rule 判断标准（三条：普遍约束 + 轻量 + 违反有后果）
§2.4 Agent 判断标准（两种：独立视角 OR 并行执行）
带着以下两个问题进入后续操作：
Q1. 这个需求应该建哪种类型？
全局约束（轻量）→ Rule
需要独立视角/并行 → Agent
其他执行流程 → Skill
Q2. 这个组件的认知根文档是什么？
即：它执行的工作，对应认知结构中哪个 L1/L1.5 文档？
常见错误（本规则防止）
❌ 用户说「我有个 Skill 想法」
→ AI 直接进入 role-Skill产品经理 或 skill-designer 做 Skill 设计
→ 但该需求其实应建 Rule（全局约束）或 Agent（需要独立视角）
✅ 正确：先按 §2.5 决策树确认类型，再进入对应流程
❌ 用户说「修改这个 Skill」
→ AI 直接修改，未确认修改与认知根一致
✅ 正确：Step 1.5 读原则文档，确认修改不会让组件偏离认知根
❌ 体系不断新增 Skill 设计类 Skill，但每个都要手工加 D0 行才能看到三型框架
✅ 正确：本 Rule 统一守门，无论哪个 Skill 被触发都会有原则文档背景
与其他组件的关系
| 组件 | 关系 | 说明 |
|---|---|---|
skill-designer |
本规则是其前置守门 | skill-designer 自身也有 D0 行，两者双重保障 |
skill-rule-修改规范 |
本规则是其前置守门 | 修改规范 Step 1.5 也读原则文档，两者双重保障 |
role-Skill产品经理 |
本规则补全其缺失 | v1.1 已补 D0，但本规则提供额外的体系级保障 |
Skill体系设计原则_v1.0.md |
本规则的单一真源 | 所有三型判断知识来源于此，本规则只是导流入口 |
变更记录
v1.0 — 2026-03-23 — 初始创建
根因：严格基于代码分析发现：role-Skill产品经理 无知识导航表，不读 Skill体系设计原则_v1.0.md，导致只能处理 Skill 产品定义而不知道 Rule/Agent 类需求的存在。根本原因不是单个 Skill 的 D0 缺失，而是原则文档与 Skill 设计类任务的连接机制依赖人工逐个添加，有系统性漏洞——任何新建的 Skill 设计类 Skill 若忘记加 D0 就会落入盲区。
设计决策：alwaysApply: false（条件触发）——仅在 Skill/Rule/Agent 设计类任务时激活，避免不相关任务注入额外 context。
配套修复：同步修改 role-Skill产品经理 v1.1，补充知识导航表 D0 + Step 0 三型确认。
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.
- 10d ago First seen · 92 lines · 168 tokens per session scan A 412c5972f8e4
skill-design-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 168 tokens to every session and 1,369 once invoked, about $0.0008 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 cursor rules, from other repositories
10-feature-development
Feature implementation workflow and engineering mindset.
11-template-conventions
Reusable building blocks shipped with this template - use them instead of writing new ones.
03-ui
UI, layout, theming and localization standards.
09-android-best-practices
Android engineering best practices.
12-new-project
Workflow for starting a new app from this template - rebranding, identity, cleanup and first feature.
13-updating-project
Workflow for updating an existing project - dependency and SDK upgrades, migrations, refactors, bug fixes.