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/cognitive-structure-write-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/cognitive-structure-write-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/cognitive-structure-write-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/cognitive-structure-write-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/cognitive-structure-write-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 | $0.00086 | $0.02209 |
| Opus 5 | $0.00043 | $0.01104 |
| Sonnet 5 | $0.00017 | $0.00442 |
| Haiku 4.5 | $0.00009 | $0.00221 |
Grade A, and why
cognitive-structure-write-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 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
认知结构写保护规则(Cognitive Structure Write Guard)
核心原则
写入L1或L1.5文档,不是一个简单的文件修改操作,而是对「系统唯一真相」的变更,必须完整执行下面的流程。
触发条件
当 AI 准备对以下路径中的文件执行 Write 操作时,本规则强制生效:
_内部总控/认知结构/L1_系统性文档/下的任何.md文件_内部总控/认知结构/L1.5_底层原则层/底层原则库.md
⚠️ 写入前路径合法性检查(新增,2026-03-20):
在执行任何写入之前,先验证路径:
- 目标路径是否在
_内部总控/认知结构/的合法子目录内?- 合法:
L1_系统性文档/[维度]/、L1.5_底层原则层/、L2_碎片化思考/、L3_原始记录/、[维度]/知识库/ - 不合法(常见错误路径):
产品定义/、项目群/、_内部总控/(非认知结构子目录)
- 合法:
- 若路径不合法 → 立即停止写入,提示: 「⚠️ 路径合法性检查失败:[目标路径] 不在认知结构合法目录内。请确认是否应该写入认知结构,或选择正确的路径(项目目录/产品定义目录等)」
例外(不触发本规则):
_内部总控/认知结构/L1_系统性文档/[任意维度]/知识库/路径下的文件 → 这些是 REF-EXT 外部参考知识,遵循「维护协议_自洽规范.md → 新增REF-EXT文档时」规则,无需版本快照/归因标注/L0更新 → 本规则的强制5步骤不适用于知识库/目录
强制执行流程(不可跳过任何一步)
写入前
检查1:版本快照与变更记录
第一次写入该文档(文档刚迁入认知结构):
→ 创建 v1.0 快照:历史版本/[文档名]_v1.0_YYYYMMDD.md
→ 新建 [文档名]_变更记录.md(记录 v1.0 的建立时间和背景)
非第一次写入(文档已有 x.0 快照): → 判断此次修改是否为「重大变更」(核心论点变化/结构重组):
- 是重大变更 → 先创建新的 x.0 快照(v2.0/v3.0...),再修改
- 是增量修改 → 直接修改,修改完成后必须在变更记录中追加一条 → 不允许跳过记录直接修改
检查2:归因标注
- 写入的内容必须包含归因标记:
- 🔵 = 用户原始思考(用户直接说的内容)
- 🟢 = AI整理(AI对用户思考的结构化提炼)
- 🟡 = AI生成(AI基于已有文档推导的新内容)
- 如果 AI 发现自己准备写入的内容没有归因标记,先标注再写入
写入后(并行执行,顺序不限,但全部必须完成)
强制1:追加变更记录
查找或新建 [文档名]_变更记录.md(与文档同目录),追加一条:
## [YYYY-MM-DD] [操作类型]
**修改位置**:[章节]
**修改摘要**:[一句话]
**归因**:[🔵/🟢/🟡]
**触发来源**:[用户指令 | Skill名称 | 矛盾消解]
强制2:更新L0大脑总地图(必须同步 L0 内所有计数引用)
- Write:
_内部总控/认知结构/L0_大脑总地图.md - 更新该文档的「最后更新时间」字段
- 如果本次修改修复了某个 Gap,更新 Gap 状态为 ✅
- ⚠️ 若新增了 L1 文档,必须同步更新以下所有位置(不允许只改其中一处): ① 框架关系图(ASCII art)中的维度篇数标注 ② 目录树区段中的维度篇数标注(如「产品理论维度/(5篇)」) ③ L1 总计数标注(如「L1_系统性文档/(18篇,6个维度)」) ④ 知识图谱版本引用(如「知识图谱_正式文档.md(v1.2,18节点22边)」)
强制3:追加系统日志
- Write:
_内部总控/认知结构/L3_原始记录/系统日志.md(append-only) - 格式:
[LOG-YYYYMMDD-NN] [Skill名称 | 直接修改] | [操作摘要] | [文档名]
强制4:更新文档分类清单(迁移操作时必须执行)
- 触发条件:当操作是「将文档从原始位置复制/迁移到认知结构」时
- Write:
_内部总控/认知结构/文档分类清单.md - 将该文档的状态从
◑ PENDING更新为★ CURRENT,并注明认知结构中的实际路径 - 不允许跳过:迁移后分类清单状态不更新 = C5 违规,必须立即修复
强制5:更新知识图谱(新增 L1 文档时必须执行)
- 触发条件:当操作是「新建一篇 L1 文档(首次写入)」时
- Write:
_内部总控/认知结构/知识图谱_正式文档.md - 在「三、文档定位总表」的 L1 表格中追加一行(文档ID / 简称 / 聚类 / 核心主张 / 认知结构位置)
- 在「二、完整关系边图」中追加新文档与现有文档的关系边(至少1条)
- 更新文件末尾的「图谱版本行」(更新篇数计数 + 关系边计数)
- 不允许跳过:新增 L1 文档后知识图谱未更新 = C3 违规,必须立即修复
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 · 138 lines · 86 tokens per session scan A ca43e9517e78
cognitive-structure-write-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 2,209 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
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.