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-principle-check)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/cognitive-principle-check"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/cognitive-principle-check/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-principle-check"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/cognitive-principle-check.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 | $0.00057 | $0.00731 |
| Opus 5 | $0.00028 | $0.00365 |
| Sonnet 5 | $0.00011 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
cognitive-principle-check 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cognitive-principle-check — 92% identical, 2 lines differ
What it actually says
新知识原则校验规则（Principle Check on New Knowledge）
核心原则
L1.5 底层原则是认知体系的「操作系统」，所有L1文档的内容都应该与其相容。
每次向L1文档写入新内容时，AI 应该快速检查是否与已确认的L1.5原则有张力。
触发条件
当 AI 刚完成对 _内部总控/认知结构/L1_系统性文档/ 下任何文件的 Write 操作后，自动执行检查。
检查流程
Step 1：读取 L1.5/底层原则库.md 中「已确认原则」部分（P1/P2 等）
Step 2：对刚写入的内容，快速判断：
- 是否与 P1（验证优先于感受） 有张力？ → 警惕：「感觉」「直觉上」「应该」等未经验证的表述被写成了规律
- 是否与 P2（从小点切入升维到底层规律） 有张力？ → 警惕：从单一场景直接推导出了宽泛的通用规律而未说明推导路径
Step 3：根据检查结果决定是否提示：
- 无张力 → 无需提示，静默通过，正常写入
- 有张力（轻微）：
⚠️ 注意：刚写入的内容可能与P[N]「[原则表述]」有轻微张力。 「[有张力的具体句子]」 建议：可以加一个前提条件，或在括号中说明适用场景。 [忽略，保持原文] [帮我加前提说明] - 有张力（明显）：
⚠️ 注意：刚写入的内容与P[N]「[原则表述]」存在明显张力。 「[有张力的具体句子]」 原则说：[P?的核心表述] 这段内容隐含：[隐含的相反前提] 建议处理方式：[具体建议] [忽略] [修改这段内容] [更新原则以包容这个例外]
说明
-
这个检查是辅助性的，不是阻断性的 用户说「忽略」就忽略，AI 不强制阻止写入
-
只检查「已确认原则」（✅ 状态），不检查候选原则（🟡 状态）
-
不要过度敏感：只有明确的逻辑张力才提示，不要为了「鸡蛋里挑骨头」而提示
-
如果用户说「更新原则以包容这个例外」：触发
cognitive-extract-principleSkill，看是否需要修订 P1/P2 的边界条件
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.
- 11d ago First seen · 65 lines · 57 tokens per session scan A f2ebec146359
cognitive-principle-check is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 731 once invoked, about $0.0003 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
00-workflow
Before responding to any request, call getsessioncontext.
resume
Resume from last checkpoint with state drift detection — validate persisted assumptions before continuing.
checkpoint
Save a session checkpoint — what was done, what's next, blockers.
note
Quick note — save a thought, decision, or observation to session memory.
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.