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-doc-versioning-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/project-doc-versioning-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/project-doc-versioning-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/project-doc-versioning-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/project-doc-versioning-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 | $0.01462 | $0.01462 |
| Opus 5 | $0.00731 | $0.00731 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
project-doc-versioning-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 10d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目文档版本留痕规则（project-doc-versioning-guard）
设计对齐：代码用 git 管理版本 / Skill·Rule·Agent 用 skill-rule-修改规范 备份 / 认知结构文档用 cognitive-structure-write-guard 备份。 本规则补全最后一层：项目级产物文档。
覆盖范围（必须执行留痕）
✅ 需要备份的文档（以下目录中已存在的 .md 文件）：
项目群/[任意项目]/下的所有文档（产品定义.md / 技术架构.md / 开发计划.md / DEPLOY_ARCH.md / 测试规范.md 等）_内部总控/开发规范/下的所有规范文档测试工程师/目录下的规范性文档- 任何其他项目级「产物型」.md（报告、审核文档、API 合约等）
❌ 排除（不需备份）：
- 追加型日志：
任务日志.md/PENDING-EXPERIENCES.md/系统日志.md/CO-BUILD-LOG.md（这些文件本身就是历史记录，只增不减） - 认知结构：
_内部总控/认知结构/L1_*/L1.5_*（由 cognitive-structure-write-guard.mdc 覆盖） - Skill/Rule/Agent 文件：
.cursor/skills//.cursor/rules//.cursor/agents/（由 skill-rule-修改规范 覆盖） - 代码文件：
.ts/.py/.tsx/.js等（由 git 管理） - 新建文件：目标路径不存在时（无旧版本可备份）
强制执行步骤（4步，顺序不可跳过）
Step 1【读取版本信息】
Read: [目标文件] 前10行
→ 找版本号（如 v1.1 / v0.5）
→ 若无版本号 → 视为 v1.0，备份为 v1.0，新版改为 v1.1
Step 2【备份到 history/】
目标路径：[文件所在目录]/history/[文件名无.md]_v[当前版本]_[YYYYMMDD].md
→ 若 history/ 目录不存在 → Shell: mkdir -p [目录]/history/
→ cp [文件] [备份路径]
→ ⚠️ 必须确认备份文件存在后才继续，不可跳过
Step 3【执行修改】
→ 更新文件头部版本号（小修改 +0.1；重大重构 +1.0）
→ 执行原计划的修改内容（StrReplace 或 Write）
Step 4【追加变更记录】
在文档末尾追加（若已有「## 变更记录」章节则在其内追加，否则新建）：
---
## 变更记录（续）
### [新版本号] — [YYYY-MM-DD] — [本次修改一句话摘要]
**修改内容**：[具体改了什么，为什么改]
**备份路径**：`history/[文件名]_v[旧版本]_[日期].md`
违反后果
直接 Write/StrReplace 而未备份 → 旧版本永久丢失，无法恢复。
与现有留痕机制的关系
| 层级 | 机制 | 覆盖范围 |
|---|---|---|
| 代码层 | Git | .ts/.py/.tsx 等代码文件 |
| 认知结构层 | cognitive-structure-write-guard.mdc | L1/L1.5 认知文档 |
| Skill/Rule/Agent 层 | skill-rule-修改规范 | .cursor/ 目录组件 |
| 项目文档层 | 本规则（project-doc-versioning-guard） | 项目群/ 和规范文档 |
变更记录
v1.0 — 2026-03-23 — 初始创建
根因：系统性审计发现项目文档层（产品定义.md / 技术架构.md / 开发计划.md 等）是留痕机制的唯一空白层。L1 认知文档和 Skill 文件均有强制备份机制，但项目文档毫无保护——一次错误的 Write 调用会导致历史版本永久丢失。
设计决策：
- alwaysApply: false（条件触发）：仅在修改项目文档时激活，不增加全局 context 负担
- 覆盖范围：项目群/ + 开发规范/（新建文件、代码文件、追加型日志排除）
- 四步强制流程：读取版本 → 备份 → 修改 → 追加变更记录
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.
- 10d ago First seen · 105 lines · 1,462 tokens per session scan A 60838d73606c
project-doc-versioning-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 1,462 tokens to every session, about $0.0073 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.