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 TashanGKD/tashan-cursor-skills --skill skill-system-health-checkgit 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/skills/tashangkd/tashan-cursor-skills/skill-system-health-check)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-system-health-check"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-system-health-check/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/tashangkd/tashan-cursor-skills/skill-system-health-check"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-system-health-check.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 | $0.00147 | $0.02330 |
| Opus 5 | $0.00073 | $0.01165 |
| Sonnet 5 | $0.00029 | $0.00466 |
| Haiku 4.5 | $0.00015 | $0.00233 |
Grade A, and why
skill-system-health-check 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 体系自洽性审查（skill-system-health-check）
对应关系：
- project-closeout → 项目文档一致性检查
- skill-system-health-check → Skill/Agent/Rule 体系一致性检查
强绑定 Rule：R2 NO_FABRICATION / R3 READ_FIRST / R6 ARTIFACT_FIRST
知识导航表（执行前必须理解的概念根）
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| D0 认知根（必读） | _内部总控/认知结构/L1_系统性文档/系统架构思维维度/自进化智能体系统形式规范_v1.0.md |
层3：C1完全可观测性（所有对象必须在R中注册）；C2关系显式化（依赖必须声明）；C3类型感知变更 |
| D3 规范参考 | _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 |
§4 文档体系与知识层次（区分B/K/S对象的存放位置） |
| D4 运行时数据 | .cursor/skills/skill-index/SKILL-INDEX.md + .cursor/rules/role-menu.mdc |
R注册表（B-objects）+ 路由入口（检查一致性的两个核心文件） |
核心概念速查： ① C1违反 = SKILL-INDEX中有的对象，文件系统中不存在（或反之）→ 孤立组件 ② C2违反 = Skill引用了某Rule但未声明，该Rule变化时Skill不会收到通知 → 版本漂移 ③ 健康检查的输出是R的一致性报告，发现P0问题时必须立即路由修复，不可先放着
激活后立即执行
Step 1 读取 Skill 体系全量索引（R3 READ_FIRST）
用 explore 子智能体并行读取：
- .cursor/skills/skill-index/SKILL-INDEX.md（必读）
- .cursor/rules/role-menu.mdc（必读）
- .cursor/rules/ 目录下所有 .mdc 文件的 description 字段
- .cursor/skills/ 目录结构（验证 SKILL-INDEX 与实际文件是否对齐）
- .cursor/agents/ 目录结构（验证子智能体注册是否完整）
Step 2 执行六维自洽性检查
【维度1：触发词冲突检查】
对照 role-menu.mdc 和每个 Skill 的 description：
→ 有没有两个 Skill 的触发词高度重叠（语义相似度 > 70%）？
→ 用户说某句话，会同时匹配两个 Skill 吗？
→ 有没有 Skill 的触发词已被更精确的新 Skill 覆盖但旧 Skill 未更新？
【维度2：孤立组件检查】
→ 有没有在 SKILL-INDEX 里注册但在 role-menu.mdc 里没有的 Skill？
→ 有没有被其他 Skill/Agent 调用但未在 SKILL-INDEX 注册的组件？
→ 有没有在 role-menu.mdc 的「配套文件」表格里引用但不存在的文件路径？
【维度3：版本漂移检查】
→ SKILL-INDEX 里记录的版本号，与实际 SKILL.md 底部变更记录中的最新版本是否一致？
→ 有没有 Skill 被修改了但 SKILL-INDEX 版本号没有更新？
【维度4：alwaysApply Rule 叠加矛盾检查】
→ 读取所有 alwaysApply: true 的 Rule 文件
→ 检查：有没有两条规则在同一场景下指向相反的行为？
→ 检查：knowledge-integrity-rules.mdc 的 R1-R15 与其他 Rule 是否有冲突？
【维度5：子智能体 I/O 契约检查】
→ 所有 .cursor/agents/*.md 的 description 是否都说明了：谁调用它、输入是什么、输出是什么？
→ 有没有子智能体被 Skill 调用但该子智能体文件不存在？
【维度6：PENDING-SKILLS 状态一致性】
→ PENDING-SKILLS.md 里标注为「已完成」的 Skill，在 SKILL-INDEX 里是否存在？
→ PENDING-SKILLS 里的 P0 项是否长期未处理（超过 2 周）？
Step 3 输出「Skill 体系健康报告」（R6：必须写文件）
写入：.cursor/skills/skill-index/skill-health-report-YYYYMMDD.md
Step 4 路由后续动作
P0 问题（触发词严重冲突 / 文件路径错误 / alwaysApply 矛盾）：
→ 立即输出警告标注：「🔴 P0 问题需要立即修复——此问题会导致 Skill 体系无法正常工作」
→ 自动引导用户修复：「建议说「这里有个规范问题，帮我修复」，触发 project-convention-resolver（E类：Skill/Rule文件），由其统一记录+路由执行 skill-rule-修改规范+验证闭环」
→ 告知用户：「P0 问题未修复时，不建议继续使用相关 Skill」
P1 问题（版本漂移 / 孤立组件 / 描述不清晰）：
→ 加入 PENDING-SKILLS 或在本次立即修复（用户选择）
P2 问题（优化项）：
→ 告知用户，建议下次 skill-evolution-planner 运行时一并考虑
What ships with it
2 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.
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 First seen · 166 lines · 147 tokens per session scan A adbcedf14acf
skill-system-health-check is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 147 tokens to every session and 2,330 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
analyze
Deep codebase analysis — complexity, coupling, dead code, tech debt hotspots.
explore
Read-only codebase exploration — understand structure, data flow, and conventions before changing anything.
incident
Production incident response — structured triage, hypothesis tree, safe remediation, incident record.
android-feature
Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…
template-helpers
Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…
android-new-project
Workflow for turning a fresh copy of this Android template into a new app — renaming the package/namespace/applicationId, branding (icons, splash, palette, fonts), Firebase setup, signing config, stripping unused sample screens, and verifying the foundation. Use when the user says they are starting a new app…