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/tashangkd/tashan-cursor-skills/document-reference-guardgit 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-reference-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/document-reference-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/document-reference-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 | $0.00098 | $0.01177 |
| Opus 5 | $0.00049 | $0.00589 |
| Sonnet 5 | $0.00020 | $0.00235 |
| Haiku 4.5 | $0.00010 | $0.00118 |
Grade A, and why
document-reference-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 5d 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.
What it actually says
文档引用留痕与级联更新规则(document-reference-guard)
设计依据:F-033(引用留痕)+ F-034(引用级联更新),2026-03-20 核心原则:依赖可追溯,变动必传播。
触发条件
以下任一情况触发本规则:
场景A:新引用一个文档
- AI 在 Skill/Rule/文档中写下某个文件路径并引用其内容
- 例:role-后端开发 Step 1 新增「Read: 某个新文档.md」
场景B:被引用的文档发生变动
- 移动路径(迁移到其他目录)
- 更新内容(重大修改,如新增章节/更改格式要求)
- 版本化(创建 v2.0,旧版归档)
- 归档(移到 history/ 目录)
激活后执行
场景A:新引用一个文档
Step 1 在被引用的文档末尾,追加或更新 ## 引用记录 节:
格式:
## 引用记录
| 引用方路径 | 引用位置(章节/步骤)| 引用日期 | 引用用途 |
|---|---|---|---|
| .cursor/skills/role-后端开发/SKILL.md | Step 1 | 2026-03-20 | 读取技术架构 |
Step 2 若被引用文档不存在 ## 引用记录 节,自动创建(在文件末尾追加)
Step 3 告知用户:「✅ 引用留痕已更新:[文档路径] 的引用记录已追加」
场景B:被引用文档发生变动
Step 1 读取该文档的 ## 引用记录 节(若不存在,跳到 Step 4)
Step 2 列出所有引用方:
「此文档被以下位置引用,变动后需要同步更新:
- [引用方1]([引用位置])
- [引用方2]([引用位置])」
Step 3 对每个引用方:
IF AI 可以自动更新(路径变更/文件名变更)→ 直接更新,告知用户
IF 需要人工判断(内容语义变化)→ 标注「⚠️ 需人工确认是否需要更新引用方」
Step 4 若无引用记录节 → 告知用户:
「此文档没有引用记录,无法自动追踪引用方。建议手动检查是否有其他文件引用了它。」
引用记录节格式(模板)
被引用文档的末尾应包含此节:
## 引用记录
> 本节由 document-reference-guard 规则自动维护
> 最后更新:YYYY-MM-DD
| 引用方路径 | 引用位置 | 引用日期 | 引用用途 | 状态 |
|---|---|---|---|---|
| .cursor/skills/[Skill名]/SKILL.md | Step N | YYYY-MM-DD | [用途说明] | ✅ 有效 |
与现有体系的关系
| 现有组件 | 关系 |
|---|---|
cognitive-update-knowledge Step 6 |
本规则补充:Step 6 更新「联动文档」,本规则追加「反向引用方更新」 |
RULE-04(创建文件时声明关联关系) |
本规则补充:RULE-04 是「单向出向声明」,本规则补充「双向引用追踪」 |
cognitive-structure-write-guard |
并列:写 L1 文档时两个规则都会激活,互不冲突 |
变更记录
v1.0 — 2026-03-20 — 初始创建
根因:用户 20260320 提出 F-033(引用留痕)+ F-034(引用级联更新)原则,当前体系任何文档被引用/变动都不会触发级联检查,导致长期积累引用断链。文档被移动后,引用方如 Skills 里的 Read 路径会失效但无法感知。
设计决策:
- 约束类型:场景触发(非 alwaysApply),避免每次对话都执行此检查
- 触发时机:只在「发生引用行为」或「引用的文档变动」时激活
- 实现策略:渐进式——先从高频引用文档(写作手册/公共模块注册表等)开始补录 ## 引用记录 节
验证状态:🔵 待验证(下次文档引用/移动时验证)
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.
- 5d ago First seen · 101 lines · 98 tokens per session scan A db4e5ceade67
document-reference-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 98 tokens to every session and 1,177 once invoked, about $0.0005 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.