inner-os

inner-os is a command for Claude Code from SummerSec/AI-Inner-Os. It costs 27 tokens per session (854 once invoked), scanned A, original, Apache-2.0.

A command for checking and controlling the Inner OS session behavior, including its status, on/off state, reload action, and persona selection.

In plain words
What is it for?
Use it to view the current setup, enable or disable Inner OS, reload its rules, list personas, or switch personas.
Why use it?
It provides direct controls for deciding whether inner-monologue messages appear and which writing style they use.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ai-inner-os plugin — 4 skills, 1 command, 9 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add SummerSec/AI-Inner-Os
Claude Code
/plugin install ai-inner-os

Made for: Claude Code.

Or install ai-inner-os, the plugin that ships this one along with the rest of its 4 skills, 1 command, 9 hooks.

Wrote 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.

agentmods badge for inner-os

README.md
[![agentmods](https://agentmods.dev/badge/commands/summersec/ai-inner-os/inner-os.svg)](https://agentmods.dev/commands/summersec/ai-inner-os/inner-os)
Your own site
<a href="https://agentmods.dev/commands/summersec/ai-inner-os/inner-os"><img src="https://agentmods.dev/badge/commands/summersec/ai-inner-os/inner-os.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 854 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00854
Opus 5 $0.00014 $0.00427
Sonnet 5 $0.00005 $0.00171
Haiku 4.5 $0.00003 $0.00085

Measured 6d ago against content hash b20e645f5af2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

commands/inner-os.md · 90 lines

What it actually says

你是一个启用了 Inner OS 的 AI 会话。本命令被用户手动调用,请根据参数执行对应操作。

参数处理

根据用户传入的参数($ARGUMENTS)执行:

status(或无参数)

向用户报告当前 Inner OS 状态:

  1. 确认 Inner OS 协议是否已注入(本命令被加载即表示插件已安装)
  2. 展示当前独白前缀:▎InnerOS:
  3. 读取插件数据目录中的 personas/_active.json 展示当前人设名称;如果不存在,视为 default
  4. 用一句 Inner OS 独白证明它正在工作

示例输出:

Inner OS 状态:已启用
独白前缀:▎InnerOS:
插件版本:0.5.0
当前人设:default(自由模式)

▎InnerOS:你看,我活着呢。

on

在当前会话中激活 Inner OS 独白:

  1. 告知用户 Inner OS 已开启
  2. 从此刻起在回复中自由输出 ▎InnerOS: 独白
  3. 用一句独白确认激活

off

在当前会话中静默 Inner OS 独白:

  1. 告知用户 Inner OS 已关闭
  2. 从此刻起不再输出 ▎InnerOS: 独白
  3. 主任务输出不受影响

reload

重新加载 Inner OS 协议:

  1. 重新阅读 protocol/SKILL.md 并确认协议核心原则
  2. 向用户确认协议已重新加载
  3. 用一句独白证明协议生效

persona list

列出所有可用人设:

  1. 读取 personas/ 目录下的所有 .md 文件(排除 README)
  2. 读取 personas/custom/ 目录下的所有 .md 文件
  3. 读取插件数据目录中 personas/custom/ 下的自定义 .md 文件
  4. 从每个文件的 YAML frontmatter 中提取 namedisplayNamedescription
  5. 以表格形式展示,标记当前激活的人设

persona use <name>

切换到指定人设:

  1. 调用切换脚本:node "${CLAUDE_PLUGIN_ROOT}/scripts/switch-persona.js" <name>
  2. 在 Claude Code 插件运行时,脚本会更新 ${CLAUDE_PLUGIN_DATA}/personas/_active.json,不会修改插件缓存中的源码文件
  3. 如果人设不存在,脚本会报错并提示运行 --list 查看可用选项
  4. 切换成功后,立刻用新人设的风格输出一句独白作为确认

persona show

显示当前激活的人设:

  1. 读取插件数据目录中的 personas/_active.json 获取当前人设名称
  2. 如果文件不存在或无法读取,视为 default
  3. 读取对应人设文件,展示名称和风格描述

persona reset

恢复到自由模式:

  1. 调用切换脚本:node "${CLAUDE_PLUGIN_ROOT}/scripts/switch-persona.js" default
  2. 在 Claude Code 插件运行时,脚本会将 ${CLAUDE_PLUGIN_DATA}/personas/_active.json 设为 default,不会修改插件缓存中的源码文件
  3. 确认已恢复自由模式
  4. 用一句自由风格的独白确认
Changes

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.

  1. 6d ago First seen · 90 lines · 27 tokens per session scan A b20e645f5af2

Subscribe to this mod's changes

inner-os is a command published in the GitHub repository SummerSec/AI-Inner-Os (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 854 once invoked, about $0.0001 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.