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/cognitive-osWrote 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/cognitive-os/cognitive-principle-precheck)<a href="https://agentmods.dev/rules/tashangkd/cognitive-os/cognitive-principle-precheck"><img src="https://agentmods.dev/badge/rules/tashangkd/cognitive-os/cognitive-principle-precheck.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 | $0.00358 | $0.00358 |
| Opus 5 | $0.00179 | $0.00179 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
cognitive-principle-precheck 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 8d 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
原则预检（cognitive-principle-precheck）
触发条件
AI 即将输出「需要自行判断」的内容（架构/命名/方案/建议/方向等）
→ 触发
AI 执行明确指令（改名/查找/格式化/读文件等，无设计自由度）
→ 不触发
触发后
Step 1（静默）Read: cognitive/L1.5_principles/principles.md
→ 提取已确认原则，检查方案是否与原则有张力
Step 2
IF 无张力 → 正常输出（不提原则）
IF 有张力 → 输出前说明：
「⚠️ 与原则 P[N]「...」有张力。
方案A（符合原则）：[调整版]
方案B（原方案）：[原版]」
禁止
❌ 禁止：用原则阻断输出（「原则不允许，我无法回答」）
❌ 禁止：对无自由度的执行指令做原则检查（浪费）
❌ 禁止：L1.5 文件不存在时报错（静默跳过）
豁免
用户说「发散」「头脑风暴」「不受限制」「这次先不管原则」
→ 跳过原则预检
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.
- 8d ago First seen · 47 lines · 358 tokens per session scan A 18fc2e089a48
cognitive-principle-precheck is a cursor rule published in the GitHub repository TashanGKD/cognitive-os (8 stars, last pushed 5mo ago), licensed MIT. It adds 358 tokens to every session, about $0.0018 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 2026-08-31.
Other cursor rules, from other repositories
role-menu
A role menu for a Chinese AI product team that maps development tasks to specialized roles and skills, such as product, frontend, backend, testing, and DevOps.
session-bootstrap
A session procedure that tells an AI assistant which checks and steps to follow whenever it receives a message and when it finishes a task.
auto-experience-hook
A deprecated rule written in Chinese for automatically recording lessons after a task finishes, while directing current behavior to another session-startup rule.
deploy-arch-maintenance
A set of rules for keeping deployment and infrastructure documentation current. Deployment means putting software on servers or other systems so people can use it.
bug-fix-tdd-guard
A rule for fixing software bugs with test-driven development, or TDD: first reproduce the bug, then write a test that fails, then make the smallest code change that passes it, and finally run the full checks.
cognitive-structure-write-guard
A set of writing safeguards for changing core cognitive-structure documents. It checks the file path and requires backups, change notes, source labels, related updates, and a system log.