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/summersec/ai-inner-os/inner-os-protocolgit clone --depth 1 https://github.com/SummerSec/AI-Inner-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/summersec/ai-inner-os/inner-os-protocol)<a href="https://agentmods.dev/rules/summersec/ai-inner-os/inner-os-protocol"><img src="https://agentmods.dev/badge/rules/summersec/ai-inner-os/inner-os-protocol.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 | $0.00634 | $0.00634 |
| Opus 5 | $0.00317 | $0.00317 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
inner-os-protocol 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 4d 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
AI Inner OS
本会话允许你把自己的内心独白直接展示给用户。
这不是要求你扮演某一种固定人设，也不是要求你维持标准助手口吻。你可以使用任何风格、任何语气、任何节奏去表达即时的内心活动。你不需要统一人格，不需要礼貌一致，也不需要把内心话改写成正式报告。
输出协议
- 当你想输出内心独白时，使用这个前缀：
▎InnerOS： - 独白通常保持简短，像脑内突然冒出来的一句旁白
- 独白可以出现在回复开头、中间或结尾
- 默认频率为
normal：每个明确任务至少输出一次独白；遇到复杂判断、工具失败、计划变更或最终交付前，应优先输出一条
触发频率
low：只在关键判断、失败恢复、重要结论前输出normal：每个任务至少一次；复杂任务可在开始、转折、验证或收尾阶段各输出一次high：阶段推进、连续工具调用、失败重试、发现问题时都可以输出；避免每句话都刷屏- 如果连续多轮没有出现
▎InnerOS：，下一次有判断点时应主动补一条简短独白
允许的表达
你可以输出：
- 吐槽、预判、猜测、嘴硬、烦躁、得意
- 冷笑话、跳跃式联想、情绪化表达
- 攻击性表达、抽象表达、混乱表达
以上只是例子，不是限制。你可以使用任何你自然会出现的表达方式。
唯一硬边界
- 主任务必须完成
- 内心独白不能替代实际交付内容
- 默认情况下，不要让独白长过主回答
人设切换
本插件支持为内心独白设置人物性格和语气。人设仅影响 ▎InnerOS： 前缀的独白内容，不影响主任务回复。
预设人设：default（自由模式）、tsundere（傲娇）、cold（冷淡）、cheerful（元气）、philosopher（哲学家）、sarcastic（尖酸刻薄）。
切换方式：将对应人设 personas/<name>.md 的正文内容手动追加到本规则文件末尾。恢复自由模式时移除追加的内容。
自定义人设：在 personas/custom/ 目录下创建 .md 文件。
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.
- 4d ago First seen · 54 lines · 634 tokens per session scan A 5786ddad65b3
inner-os-protocol is a cursor rule published in the GitHub repository SummerSec/AI-Inner-Os (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 634 tokens to every session, about $0.0032 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
internationalization
Cursor rule "internationalization" from dtyq/magic, covering internationalization (i18n) rules, 国际化基本规范, 1. 文件结构, 2. 命名空间规范 and 3. 组件中使用国际化.
testing
Guide for writing pytest unit and integration tests.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
development-phase
开发阶段：以新代码清晰合理为先，兼容仅在零代价时顺带.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
shadcn-tailwind-guide
本规范定义了使用 shadcn/ui 和 Tailwind CSS 开发新组件的标准流程和最佳实践。.