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 cross-project-coordinatorgit 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/cross-project-coordinator)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/cross-project-coordinator"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/cross-project-coordinator/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/cross-project-coordinator"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/cross-project-coordinator.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 | $0.00137 | $0.01833 |
| Opus 5 | $0.00068 | $0.00916 |
| Sonnet 5 | $0.00027 | $0.00367 |
| Haiku 4.5 | $0.00014 | $0.00183 |
Grade A, and why
cross-project-coordinator 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 8d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
跨项目并行开发协调框架创建(cross-project-coordinator)
RULE-37 的执行层落地:把「必须建协调框架」的规则转化为「如何一步步建」的操作流程。
触发判断
触发条件(满足任一即触发):
- 用户提到同时要推进 2 个或以上子项目
- 不同子项目存在 API 调用关系(A 调用 B 的接口)
- 多名开发者分别负责不同子项目
触发判断示例:
- ✅「我们要同时做 twin-engine 后端和 tashan-world 前端」→ 触发
- ✅「后端开发者和前端开发者今天各自开工」→ 触发
- ❌「我要做 A 功能,做完再做 B 功能」(顺序不并行)→ 不触发
- ❌「帮我更新某个 Skill」→ 不触发
激活后立即执行
Step 0 确认触发
问用户(或从上下文推断):
「本次并行开发涉及哪些子项目?每个项目大致做什么?」
收集:项目名称列表 + 每个项目的一句话职责描述
Step 1 检查元项目导航
Read: _内部总控/元项目导航.md
→ 确认各子项目是否已在导航中(未登记的需同步更新)
→ 获取各子项目的产品定义.md 和技术架构.md 路径
Step 2 检查是否已有协调框架文档
检查 _内部总控/ 目录下是否已有 [生态名]_跨项目协调框架.md
已有 → 读取现有文档,判断是否需要追加更新(新增项目/新接口)
未有 → 执行 Step 3-6 全量创建
Step 3 生成「项目地图」(第一章)
对每个子项目输出:
- 职责:做什么(一句话)+ 不做什么(边界声明)
- 部署位置:服务器 + 端口
- 格式:ASCII 表格或 mermaid 图
Step 4 生成「跨项目 API 契约」(第二章)
对每一对存在调用关系的项目对(A→B):
接口已定义时:
列出端点 + HTTP方法 + 路径 + 关键请求/响应字段 + 鉴权方式
接口未定义时(❗关卡A发现的问题,修复:先输出占位符):
「⚠️ [端点名] — 接口待定义,建议由 [项目A] 技术架构师填写」
留占位符行,不留空白
必须包含错误码规范(见模板格式)
Step 5 生成「并行开发轨道」(第三章)
并行判断规则:
- 两个工作包之间没有共享的「输出 → 输入」依赖 → 可并行
- 例:后端 API 定义完成后,前端才能开始联调 → 串行约束
用时间轴格式输出:
- 轨道A:[项目A的工作](可立刻开始/依赖X完成后开始)
- 轨道B:[项目B的工作](同上)
- 阻塞关系:明确列出「A的X完成前,B的Y无法开始」
Step 6 生成「各项目启动前提清单」(第四章)
对每个子项目开发者的 Day 1 清单:
✅ 已就绪的文档(列路径)
🔲 缺失的文档(标注谁负责/何时完成)
✅ 可以先 mock 开始的工作(说明 mock 约定)
Step 7 保存文档
路径:_内部总控/[生态名称]_跨项目协调框架.md
关系声明(写在文档头部):
「关系类型:implements → _内部总控/AGENT_RULES.md RULE-37」
同步更新 元项目导航.md:
- 在「跨项目并行协调文档」行补充本文档路径
Step 8 触发 F-022 挑战者反思(高依赖度文档必做)
以「消费方开发者」和「接口破坏者」双视角检查:
1. API 契约是否完整(每个接口都有错误码规范?)
2. 并行轨道依赖关系是否漏写?
3. 有没有"循环依赖"(A等B,B等A)?
发现问题 → 立即修复再输出
文档模板(保存时使用)
# [生态名] · 跨项目并行开发协调框架
> 关系类型:implements → _内部总控/AGENT_RULES.md RULE-37
> 创建日期:YYYY-MM-DD
> 维护规则:任何跨项目 API 变更,必须先更新本文档,再通知消费方
## 一、项目地图
[项目地图内容]
## 二、跨项目 API 契约
[API 契约内容]
**错误码规范**:
| 状态码 | 含义 | 前端行为 |
| 400 | 请求格式错误 | 显示具体字段错误 |
| 401 | 未认证 | 跳转登录页 |
| 403 | 无权限 | 提示无权操作 |
| 404 | 资源不存在 | 显示友好提示 |
| 429 | Rate Limit | 禁用按钮N秒 |
| 5xx | 服务器错误 | 通用错误提示 |
**Mock 数据约定**:
- Mock 文件位置:[前端项目]/src/mocks/[被调用服务]/
- 格式:与 API 契约返回字段完全一致的 JSON fixture
## 三、并行开发轨道
[轨道内容]
## 四、各项目启动前提清单
[清单内容]
## 五、接口变更通知规则
任何一方变更跨项目接口时:
1. 先更新本文档
2. 在对方项目追踪台创建 P1 问题
3. 任务日志标注「跨项目接口变更」
## 六、变更记录
| 日期 | 变更 | 触发原因 |
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.
- 8d ago First seen · 169 lines · 137 tokens per session scan A 9b7dc5047b61
cross-project-coordinator is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 137 tokens to every session and 1,833 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
frappe-impl-workflow
Use when implementing document Workflows, approval chains, or state-based transitions in Frappe. Prevents stuck documents from missing transitions, broken approval chains, and permission errors on workflow actions. Covers Workflow DocType, Workflow State, Workflow Action, transition rules, allowed roles, conditions…
team
Coordinate parallel work across multiple Cursor sessions via shared .omc/team/ state.
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-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…
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…
android-preflight
Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…