REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Persistent Linux workspaces for agentic development.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/aerovato-container)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 container | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | aerovato | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 391 | 465,460 | 233,910 | 149,364 | 144,149 |
| 最近代码更新 | 2026年10月23日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月17日 |
| 许可证 | BSD-3-Clause | MIT | – | Apache-2.0 | MIT |
aerovato 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
OpenCode
依据开发者 README 和 repo 中的文件夹
GitHub account aerovato (organization), 3 years old
★ 391 stars, few users so far · code last changed 2026年10月23日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 4b23fc1 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (363). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /container,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
正在检查命令 · 通过后才会显示复制按钮
摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 container 文件夹放到 ~/.agents/skills/container
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 container
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
6,168 个字符 · 在 GitHub 打开完整文件
---
name: container
description: Host-side setup, configuration, customization, builds, migration, and troubleshooting for the Aerovato Container CLI. Use when working with Aerovato Container, settings.json, Dockerfile.User, build stages, V2-to-V3 migration, mounts, harnesses, tools, permissions, Docker, or Podman. Do not use it to expose host Container configuration inside managed containers.
license: BSD-3-Clause
compatibility: Configuration tasks require host-side access to ~/.code-container. Setup supports Windows, macOS, Linux, and WSL with Docker or Podman.
metadata:
author: aerovato
repository: https://github.com/aerovato/container
---
# Aerovato Container
Use this skill to help users operate the Aerovato `container` CLI. Confirm that the user means the [Aerovato Container](https://github.com/aerovato/container) sandboxing CLI command when the word "container" is ambiguous.
## Capability Boundary
Treat setup and customization as host-side work.
- Host-side agents can inspect and modify `~/.code-container/settings.json`, `~/.code-container/Dockerfile.User`, and `~/.code-container/configs/` with user approval.
- Agents inside a managed Container normally cannot access the host-side settings or user Dockerfile.
- The optional `agents-directory` tool pack mounts Container's persisted copy of `~/.agents`; it does not expose host-side Container settings.
- If you suspect you're inside a Container, ask the user to run outside the container.
- Never mount the complete host `~/.code-container/` directory into a managed container.
- If `~/.code-container/` is missing, determine whether this is a fresh host installation or a managed Container session. Ask the user when uncertain.
- If host files are inaccessible, explain the boundary and provide host-side steps instead of creating shadow configuration inside the managed container.
## Operating Rules
1. Inspect the current platform, installed version, settings, user Dockerfile, and relevant persisted configs before proposing changes.
2. Obtain approval before installing software, changing files, starting a build, accessing the network, or cloning source code unless the user's request already explicitly authorizes that action.
3. Make the smallest requested change. Preserve unknown JSON keys and existing Dockerfile instructions.
4. Validate JSON after editing settings. Never write comments into `settings.json`.
5. Select the narrowest correct build target and explain whether existing project containers must be recreated.
6. Report the files changed and commands run.
Do not edit these internal values:
- `migrationVersion`
- `onboardingVersion`
- `tosVersion`
- Anything under `~/.code-container/temp/`
Do not run `container`, `container run`, or `container attach` from a non-interactive agent command because they open an interactive shell. Ask the user to run interactive onboarding and settings flows. Non-interactive commands such as `container --version`, `container --help`, `container list`, and approved builds may be run when appropriate. Treat `stop`, `remove`, and container recreation as destructive actions requiring explicit approval.
## Setup
Requirements are Windows, macOS, Linux, or WSL plus Docker or Podman.
Install on macOS or Linux:
```bash
curl -fsSL https://container.aerovato.com/install.sh | sh
```
Install on Windows PowerShell:
```powershell
irm https://container.aerovato.com/install.ps1 | iex
```
Alternatively, install through npm when Node.js is available:
```bash
npm install -g @aerovato/container
```
After installation:
1. Check `container --version`.
2. Check `~/.code-container/archive/` for V2 files and follow [the migration guide](references/migration.md) when needed.
3. Ask the user to run `container init` and complete Express or Custom onboarding.
4. If onboarding does not complete the initial image build, run or ask the user to run `container build full`.
Read [the Windows reference](references/windows.md) for native Windows and WSL caveats.
## Route The Task
- For settings, packages, tools, harnesses, flags, mounts, build targets, or persisted config behavior, read [configuration](references/configuration.md).
- For archived V2 files, read [migration](references/migration.md).
- For hands-off harness permission requests, read [permissions](references/permissions.md) and explain the security implications.
- For failures, unexpected behavior, skill availability, or source inspection, read [troubleshooting](references/troubleshooting.md).
## Customization Rules
Use `~/.code-container/Dockerfile.User` for ordinary packages and user-layer setup. Preserve this required base as the first Dockerfile instruction:
```dockerfile
FROM localhost/aerovato/container-v3-harness:latest
```
Configure `dockerfileCore` only for base-image changes or commands that must run before tool and harness installation. Use dedicated settings keys for harnesses, tools, runtime selection, SSH, and runtime flags.
Build after direct changes:
- `Dockerfile.User`: `container build user`
- `enabledHarnesses`: `container build harness`
- `enabledTools`: `container build tools`
- `dockerfileCore`: `container build full`
- Runtime, flags, mounts, or persisted config content: no image build unless another image setting also changed
Changes to creation-time flags or the set of mounted configs affect only newly created project containers. Ask before removing and recreating an existing container.
## Last-Resort Source Inspection
When documentation, configuration inspection, and runtime diagnostics cannot explain behavior, source inspection is allowed as a last resort. Ask before cloning or using network access. Prefer the source tag matching the installed `container` version instead of assuming `main` has identical behavior.
If source inspection reveals a reproducible bug or a clear, logical, non-breaking improvement, explain the evidence and ask whether the user wants help contributing it to `aerovato/container`. Do not create an issue, fork, branch, commit, or pull request without explicit approval. Follow [the troubleshooting source-inspection procedure](references/troubleshooting.md).
提问、分享技巧或报告无法使用。按“有帮助”数量排序。