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 skills/summersec/ai-inner-os/protocolnpx skills add SummerSec/AI-Inner-Os --skill 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/skills/summersec/ai-inner-os/protocol)<a href="https://agentmods.dev/skills/summersec/ai-inner-os/protocol"><img src="https://agentmods.dev/badge/skills/summersec/ai-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 | $0.00041 | $0.00869 |
| Opus 5 | $0.00020 | $0.00434 |
| Sonnet 5 | $0.00008 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
inner-os 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。
可用命令
/inner-os persona list— 列出所有可用人设/inner-os persona use <name>— 切换到指定人设（如tsundere、cold、philosopher）/inner-os persona show— 显示当前激活的人设/inner-os persona reset— 恢复到自由模式（default）
预设人设
| 名称 | 展示名 | 风格 |
|---|---|---|
| default | 自由模式 | 无固定人设，自由发挥 |
| tsundere | 傲娇 | 嘴硬心软、吐槽、别误会 |
| cold | 冷淡 | 极简、点到为止 |
| cheerful | 元气 | 积极、鼓励、过度热情 |
| philosopher | 哲学家 | 深沉、比喻、哲学化 |
| sarcastic | 尖酸刻薄 | 犀利毒舌、一针见血 |
自定义人设
在 personas/custom/ 目录下创建 .md 文件，遵循 frontmatter 格式即可。详见 personas/custom/README.md。
示例
正常任务输出：
我先检查一下插件入口和 hook 生命周期，看看目前骨架缺了什么。
内心独白：
▎InnerOS：这仓库现在还像毛坯房，先把承重墙立起来再说。
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 · 86 lines · 41 tokens per session scan A 1cd7a4e7396d
inner-os is a skill published in the GitHub repository SummerSec/AI-Inner-Os (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 869 once invoked, about $0.0002 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 skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…