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/multi-project-file-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/multi-project-file-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/multi-project-file-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/multi-project-file-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/multi-project-file-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 | $0.00068 | $0.02249 |
| Opus 5 | $0.00034 | $0.01125 |
| Sonnet 5 | $0.00014 | $0.00450 |
| Haiku 4.5 | $0.00007 | $0.00225 |
Grade A, and why
multi-project-file-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 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
多项目同名文件防混淆规则(multi-project-file-guard)
根本问题:同一个 workspace 下有多个项目,每个项目都有
技术架构.md、产品定义.md、DEPLOY_ARCH.md、开发计划.md等同名文件。 凭文件名搜索、凭 IDE 打开文件推断、凭「应该在这里」的直觉去操作,都会导致操作到错误项目的文件。
已知高风险重名文件清单(当前 workspace)
DEPLOY_ARCH.md → scholar-match / tashan-openbrain_myagent / tashan-world / _worktree_boyuan
技术架构.md / 技术架构_*.md → tashan-openbrain_myagent / tashan-world / ai-org-builder 等
产品定义.md → tashan-openbrain_myagent / tashan-world 等
开发计划.md → tashan-openbrain_myagent / tashan-world 等
开发规范.md → tashan-world / scholar-match 等
每次触碰以上任何文件时,必须先走「项目上下文锁定」流程。
触发条件
以下任一情况发生时,本规则强制生效:
- AI 准备 Read / StrReplace / Write 一个项目级文档(技术架构/产品定义/部署架构/开发规范等)
- 用户说「更新技术架构」「看一下部署配置」「修改开发计划」等,但没有指定完整路径
- AI 的上下文中涉及多个项目,不能确定「当前是在操作哪个项目」
- AI 通过 Glob/Grep 搜到多个同名文件
强制执行流程
Step 1 — 项目上下文锁定
在操作任何文件之前,必须先声明当前项目上下文:
【当前操作项目】:项目群/[项目名]/
【操作文件路径】:[完整绝对路径]
【确认依据】:[用户明确说明 / 对话上下文推断 / IDE 打开文件]
- 依据来自「用户明确说明」→ 直接执行
- 依据来自「对话上下文推断」→ 声明后询问用户确认,确认后再操作
- 依据来自「IDE 打开文件」→ 必须向用户确认(强制规则11:IDE状态不得劫持意图)
- 无法确定 → 向用户列出候选项,等待选择,不可猜测
Step 2 — 路径精确化
禁止使用模糊路径:
❌ 禁止:Read 技术架构.md
❌ 禁止:StrReplace 技术架构.md
❌ 禁止:「更新技术架构里的XXX」(不带完整路径)
✅ 必须:Read t:\TashanAgent4S_2026\0310_huaxiang\项目群\tashan-world\技术架构师\技术架构.md
✅ 必须:所有文件操作工具调用都包含完整绝对路径
如果之前在对话中已经声明了路径,后续操作可引用已确认路径,但不得「默默切换」到不同项目的文件。
Step 3 — 内容读取前,不允许输出分析结论
规则 R3 READ_FIRST 的多项目强化版:
❌ 禁止:未 Read 文件就输出「技术架构里面XXX是这样设计的」
❌ 禁止:基于另一个项目的文件内容去描述当前项目的架构
❌ 禁止:「这两个项目应该差不多」的假设
✅ 必须:Read 目标文件 → 解析内容 → 再分析/引用/修改
Step 4 — 跨文件引用时,验证概念逻辑自洽
当修改一个文件中的概念/设计决策时,需同时确认:
检查清单(仅当修改设计级内容时执行,不适用于纯格式修改):
□ 本文件引用了哪些其他文件的概念?(如技术架构引用产品定义中的角色/功能)
□ 被引用的概念在源文件中是否一致?(不允许概念在两个文件中有不同的定义)
□ 本次修改是否造成跨文件的不一致?(如修改了接口名称,是否同步到引用文件)
□ 所有外部引用是否都指向同一项目的文件?(不得跨项目混引)
如果发现跨文件不一致 → 在修改前告知用户,由用户决策是否同步修改。
禁止行为清单(一票否决)
❌ 凭文件名直接搜索并操作第一个结果(不看路径)
❌ 因为 IDE 当前打开了某文件就默认「用户在操作这个项目」(见强制规则11)
❌ 把 A 项目的架构设计内容写入 B 项目的文档
❌ 在不确定当前项目的情况下,自行决定路径
❌ 跨项目复用概念定义而不声明差异(「和上个项目一样」≠「不需要确认」)
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.
- 9d ago First seen · 186 lines · 68 tokens per session scan A b3a52ab062d4
multi-project-file-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 2,249 once invoked, about $0.0003 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.
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.
01-tech-stack
Android tech stack and project standards.