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/document-lifecycle-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/document-lifecycle-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/document-lifecycle-guard.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 5.1 | $0.00087 | $0.02020 |
| Opus 5 | $0.00044 | $0.01010 |
| Sonnet 5 | $0.00017 | $0.00404 |
| Haiku 4.5 | $0.00009 | $0.00202 |
Grade A, and why
document-lifecycle-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 7d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文档生命周期守门规则(document-lifecycle-guard)
核心原则: 文档不是「为这次任务新建的」,而是「被这次任务更新了」。 一个项目中,每类核心文档永远只有一份——不断演化,不断增厚,不创建平行版本。
每个角色的文档领地
每个角色在项目中有且仅有一个文件夹,这是它的唯一文档领地:
| 角色 | 文件夹 | 核心文档(最多3个) | 追踪台 |
|---|---|---|---|
| 产品经理 | 产品经理/ |
产品定义.md / 开发计划.md | 产品问题追踪台.md |
| 技术架构师 | 技术架构师/ |
技术架构.md | 技术问题追踪台.md |
| 测试工程师 | 测试工程师/ |
test-spec.md / 主测试文档.md | — |
| DevOps | DevOps/(或项目根目录) |
DEPLOY_ARCH.md | — |
| 内部总控(跨角色) | 内部总控/ |
修复记录.md | — |
文档管理铁律(所有角色必须遵守)
铁律 1:自建不等待
激活任何角色时,执行:
Glob: 项目群/[项目]/[角色文件夹]/*.md
IF 文件夹不存在 OR 核心文档缺失:
→ 立即创建(见「标准初始化模板」)
→ 不需要用户授权,不需要等待
→ 输出:「📁 已初始化 [角色] 文档领地」
铁律 2:in-place 更新,禁止创建平行版本
✅ 正确:打开 产品定义.md → 找到相关章节 → 修改内容 → 更新版本号 → 追加变更记录
❌ 禁止:创建 产品定义_v2.md / 产品定义_新版.md / 产品定义_20260325.md
❌ 禁止:创建 技术架构_修改版.md
❌ 禁止:同一角色文件夹下有超过3个核心文档(追踪台不计)
判断方法:
IF 你想创建一个文件名含「v2/新版/修改版/副本/temp」的文档 → 停止,改为更新原文档
铁律 3:所有核心文档必须有变更记录
每个核心文档底部必须有:
## 变更记录
| 版本 | 日期 | 修改内容 | 修改原因 |
|------|------|---------|---------|
| v1.0 | 初始日期 | 初始创建 | — |
| v1.1 | 修改日期 | [改了什么] | [为什么改] |
每次修改文档,必须在此表追加一行。不可省略。
铁律 4:重大改版先存旧版
判断标准:满足任一条 → 视为「重大改版」
□ 修改内容超过文档总量的 30%
□ 删除了已有章节
□ 更改了核心数据结构/接口定义
□ 产品定位/技术方向发生调整
重大改版流程:
Step 1: 将当前版本复制到 history/ 子目录
命名:[文件名]_v[当前版本]_[YYYYMMDD].md
示例:产品定义_v1.2_20260325.md
Step 2: 修改原文件内容
Step 3: 更新版本号
Step 4: 追加变更记录
IF 只是小改动(修正措辞/补充细节/修复错误描述)→ 不需要存旧版,直接改
铁律 5:追踪台文件 append-only
产品问题追踪台.md / 技术问题追踪台.md / 修复记录.md:
✅ 只追加行,不删除行
✅ 解决后更新「状态」列为「已解决」
❌ 不删除已解决的条目(需要历史追溯)
❌ 不需要存旧版(本身就是历史记录)
标准初始化模板
标准文档头(所有核心文档统一格式)
# [文档名]
> **版本**:v1.0 | **日期**:YYYY-MM-DD
> **所属角色**:[角色名] | **项目**:[项目名]
> **用途**:[一句话说明这个文档的唯一职责]
---
[正文内容]
---
## 变更记录
| 版本 | 日期 | 修改内容 | 修改原因 |
|------|------|---------|---------|
| v1.0 | YYYY-MM-DD | 初始创建 | — |
各角色标准初始文件
产品经理/:
产品定义.md ← 产品功能与行为的唯一权威描述
开发计划.md ← 任务拆解与状态跟踪(✅/🔲/❌)
产品问题追踪台.md ← 产品需求与设计问题记录
history/ ← 空目录,存重大改版旧文件
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.
- 7d ago First seen · 216 lines · 87 tokens per session scan A 00533a037572
document-lifecycle-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 87 tokens to every session and 2,020 once invoked, about $0.0004 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
documentation
Documentation: code docs, READMEs, ADRs, maintenance.
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.