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 agentmods add rules/mywand/cusrsor-do-it/feature-specification-guidelinesgit clone --depth 1 https://github.com/mywand/cusrsor-do-itWrote 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/mywand/cusrsor-do-it/feature-specification-guidelines)<a href="https://agentmods.dev/rules/mywand/cusrsor-do-it/feature-specification-guidelines"><img src="https://agentmods.dev/badge/rules/mywand/cusrsor-do-it/feature-specification-guidelines.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.08483 |
| Opus 5 | $0.00000 | $0.04241 |
| Sonnet 5 | $0.00000 | $0.01697 |
| Haiku 4.5 | $0.00000 | $0.00848 |
Grade A, and why
feature-specification-guidelines 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 3d 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 — 934 lines — stays where its author put it; the contents beside it link to each section on GitHub.
最近更新: 2025-10-11
功能规格说明文档规约
适用于中大型项目的功能需求规格说明，确保需求清晰、设计完整、验收标准明确。
1. 适用场景
1.1 项目规模
| 维度 | 适用范围 | 说明 |
|---|---|---|
| 团队规模 | > 10人 | 多团队协作 |
| 项目周期 | > 6个月 | 中长期项目 |
| 功能复杂度 | 中高 | 跨模块、多依赖 |
| 需求变更频率 | 中低 | 需要严格的需求管理 |
1.2 何时使用
✅ 适合使用：
- 大型功能开发（影响多个模块）
- 跨团队协作（需要明确接口定义）
- 外部对接（需要详细的接口文档）
- 高质量要求（需要完整的验收标准）
- 合规性要求（需要完整的文档记录）
❌ 不适合使用：
- 简单功能调整（使用用户故事即可）
- 紧急Bug修复（直接修复，事后补文档）
- 原型验证（使用轻量级需求描述）
- 小团队快速迭代（过于重量级）
1.3 与其他文档的关系
graph TB
A[产品需求文档<br/>PRD] --> B[功能规格说明<br/>本文档]
B --> C[技术设计文档]
B --> D[接口设计文档]
B --> E[测试用例]
C --> F[代码实现]
D --> F
E --> G[验收测试]
F --> G
style B fill:#0ea5e9,stroke:#0369a1,color:#fff
2. 文档管理
2.1 文件命名
feature-<功能模块>-<功能名称>-spec.md
示例：
feature-user-registration-spec.md # 用户注册功能
feature-payment-refund-spec.md # 支付退款功能
feature-order-batch-export-spec.md # 订单批量导出
2.2 文件存放
项目根目录/
├── docs/
│ ├── features/ # 功能规格目录
│ │ ├── README.md # 功能索引
│ │ ├── user/ # 用户相关功能
│ │ │ ├── feature-user-registration-spec.md
│ │ │ └── feature-user-profile-spec.md
│ │ ├── payment/ # 支付相关功能
│ │ │ ├── feature-payment-integration-spec.md
│ │ │ └── feature-payment-refund-spec.md
│ │ └── order/ # 订单相关功能
│ │ └── feature-order-export-spec.md
│ └── requirements/ # 需求文档（PRD等）
2.3 状态管理
| 状态 | 说明 | 操作 |
|---|---|---|
| 草稿（Draft） | 初稿，待补充 | 需求收集中 |
| 评审中（In Review） | 待评审 | 相关方评审 |
| 已批准（Approved） | 评审通过 | 开始设计开发 |
| 开发中（In Development） | 开发实施中 | 跟踪实施进度 |
| 已实现（Implemented） | 开发完成 | 验收测试 |
| 已验收（Accepted） | 验收通过 | 上线发布 |
| 已废弃（Deprecated） | 功能废弃 | 说明废弃原因 |
3. 文档模板
3.1 文档头部
# 功能规格说明：<功能名称>
**文档信息**：
| 项目 | 内容 |
|------|------|
| **文档版本** | v1.0 |
| **文档状态** | 草稿 / 评审中 / 已批准 / 开发中 / 已实现 / 已验收 |
| **功能编号** | FEAT-001 |
| **创建日期** | YYYY-MM-DD |
| **最后更新** | YYYY-MM-DD |
| **作者** | 姓名 / 团队 |
| **评审人** | 姓名1, 姓名2, 姓名3 |
| **相关需求** | [PRD-001](link) |
## 变更记录
| 版本 | 日期 | 变更内容 | 变更人 | 评审状态 |
|------|------|----------|--------|----------|
| v1.0 | YYYY-MM-DD | 初始版本 | 张三 | 已批准 |
| v1.1 | YYYY-MM-DD | 增加异常处理逻辑 | 李四 | 评审中 |
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.
- 3d ago First seen · 934 lines · 0 tokens per session scan A 4e881416acbf
feature-specification-guidelines is a cursor rule published in the GitHub repository mywand/cusrsor-do-it (2 stars, last pushed 7mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 8,483 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.