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/project-independence)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/project-independence"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/project-independence/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/project-independence"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/project-independence.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 | $0.00067 | $0.01271 |
| Opus 5 | $0.00034 | $0.00635 |
| Sonnet 5 | $0.00013 | $0.00254 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
project-independence 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目独立性规范(RULE-INDEP)
触发条件:任何涉及"基于 X 项目构建"、"集成第三方库"、"fork 已有仓库"的架构设计或开发任务。
核心原则
每个他山项目必须完全自包含(self-contained),运行时不依赖外部项目的私有 API 或内部实现细节。
强制规则
RULE-INDEP-1:外部代码通过「复制源码」集成,不通过「安装包后引用私有路径」
❌ 错误做法:
import { MemoryIndexManager } from "openclaw/dist/manager-runtime--abc123.js"
问题:dist 文件名含 hash,每次编译变化,私有路径无版本保证
✅ 正确做法:
1. 确认外部项目许可证允许复制(MIT/Apache 等开源许可)
2. 将所需源码目录复制到本项目内,如:
cp -r reference/repos/openclaw/src/memory/ apps/server/src/memory-engine/
3. 在文件头部注明来源:
// 来源:openclaw/src/memory/(openclaw 项目,MIT 许可)
// 原始 commit:ef7a5c3
// 与上游的差异:[列出所有修改]
4. 在 reference/repos/ 维护原始版本作为同步基准
RULE-INDEP-2:只允许依赖外部包的「公开稳定 API」
判断标准:该 API 是否出现在 package.json 的 exports 字段中?
✅ 出现在 exports → 公开 API,可以 import
❌ 不在 exports,是 dist/ 内部路径 → 私有 API,不允许 import
示例:
✅ import { something } from "some-package" ← 主入口公开 API
✅ import { x } from "some-package/plugin-sdk/core" ← exports 里声明的路径
❌ import { x } from "some-package/dist/index-abc.js" ← hash 路径,私有
❌ import { x } from "some-package/src/internal/x" ← src 内部路径,私有
RULE-INDEP-3:reference/ 目录是参考基准,不是运行时依赖
reference/repos/ ← 只读参考(git clone --depth=1 上游仓库)
opencode/ ← 用于理解架构、找到要复制的模块
openwork/ ← 作为 fork 的上游基准
openclaw/ ← 用于复制需要的源码模块
注意:
✅ 开发时阅读 reference/ 理解代码
✅ 从 reference/ 复制源码到自己项目
❌ 运行时让项目代码 import from reference/ 路径
❌ 把 reference/ 里的包安装为 npm 依赖后引用私有路径
RULE-INDEP-4:Fork 项目必须明确声明「何时与上游同步」
每个 fork 的项目必须有:
1. TASHAN-ARCHITECTURE.md(或等效文档)声明上游仓库和 commit hash
2. 说明哪些文件是「从上游复制但做了修改」及修改原因
3. 定义上游同步策略:
- 跟随上游:定期 git merge upstream/main
- 定点冻结:只在有明确需求时手动同步特定模块
例外情况
以下情况允许直接安装并使用外部包:
| 情况 | 条件 |
|---|---|
| 使用 npm 包的公开 API | 必须出现在 package.json exports 中 |
| 使用广泛使用的工具库 | 如 zod / @sinclair/typebox / bun:sqlite 等标准工具 |
| 已发布稳定 npm 版本的模块 | 版本锁定在 package.json 中 |
触发后立即执行
1. 检查本次架构/开发是否涉及引用外部项目代码
2. 若涉及:
□ 该代码是否通过 package.json exports 公开暴露?
是 → 可以安装包并 import
否 → 必须复制源码
□ 如复制源码:是否在文件头部注明来源和修改记录?
□ reference/repos/ 是否已有该上游仓库的 git clone?
3. 在架构文档的「依赖策略」章节声明
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 · 119 lines · 67 tokens per session scan A f6a7f7cd0fce
project-independence is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 1,271 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.
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.
02-architecture
Architecture rules - MVVM baseline, MVI for complex features.