Container

Organization

aerovato

container

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.

Overview

Publisher	aerovato
Repository	`container`
Skill name	`container`
Stars	354
Forks	34
Bundled files	5
License	BSD-3-Clause
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by aerovato on GitHub. Read the source before you install it.

Installation

Install the Container AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/aerovato/container/tree/main/skills/container
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/aerovato/container.git /tmp/container
mkdir -p .claude/skills
cp -r /tmp/container/skills/container .claude/skills/container

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Container in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Container on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Container is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Aerovato Container

Use this skill to help users operate the Aerovato container CLI. Confirm that the user means the 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

Inspect the current platform, installed version, settings, user Dockerfile, and relevant persisted configs before proposing changes.
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.
Make the smallest requested change. Preserve unknown JSON keys and existing Dockerfile instructions.
Validate JSON after editing settings. Never write comments into settings.json.
Select the narrowest correct build target and explain whether existing project containers must be recreated.
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:

Check container --version.
Check ~/.code-container/archive/ for V2 files and follow the migration guide when needed.
Ask the user to run container init and complete Express or Custom onboarding.
If onboarding does not complete the initial image build, run or ask the user to run container build full.

Read the Windows reference for native Windows and WSL caveats.

Route The Task

For settings, packages, tools, harnesses, flags, mounts, build targets, or persisted config behavior, read configuration.
For archived V2 files, read migration.
For hands-off harness permission requests, read permissions and explain the security implications.
For failures, unexpected behavior, skill availability, or source inspection, read troubleshooting.

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.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Container AI skill do?

Why use Container on TypingMind?

Because you install it once and use it with any model. Container is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Container in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aerovato/container/tree/main/skills/container. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Container?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Container?

As many as you like. As long as a model supports skills, you can use Container with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Container AI skill free?

Yes. It is published on GitHub by aerovato under the BSD-3-Clause license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Test Performance

openclaw

OrganizationPopular

Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

Openclaw Testing

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Release Openclaw Ci

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

Release Openclaw Mac

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Aerovato Container

Capability Boundary

Operating Rules

Setup

Route The Task

Customization Rules

Last-Resort Source Inspection

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now