Github Airplane Mode logo

Github Airplane Mode

Community
vincentkoc
github-airplane-mode

Inspect or switch the local Git and GitHub download guard using an already-installed compatible low-data command. Use for airplane mode, flight or metered connections, returning online, or requests to enable, disable, or automatically select low-data protection on this machine.

Overview

Publishervincentkoc
Repositorydotskills
Skill namegithub-airplane-mode
Stars
112
Forks
9
Bundled files
2
LicenseMIT
Links
  • 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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vincentkoc on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vincentkoc/dotskills/tree/main/skills/github-airplane-mode
  4. 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.
2

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/vincentkoc/dotskills.git /tmp/dotskills
mkdir -p .claude/skills
cp -r /tmp/dotskills/skills/github-airplane-mode .claude/skills/github-airplane-mode
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Airplane Mode 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 Github Airplane Mode 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 Github Airplane Mode 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.

GitHub Airplane Mode

Purpose

Switch an already-installed local Git and GitHub download guard.

Keep the guard installed and active sessions intact. This skill does not bundle or install low-data, Git/GitHub wrappers, or a native connection-cost detector.

When to use

  • Enable protection before a flight or on a metered connection.
  • Disable protection after returning online.
  • Inspect the current policy or use automatic connection-cost detection.

Workflow

Verify the prerequisite

Operate only on the current machine. Require an already-installed compatible low-data command before running any recipe.

  1. Resolve command -v low-data and inspect its file or symlink target. Verify its trusted local source and the mode, status, and exit semantics below. Stop if it is missing, shadowed, unfamiliar, or incompatible; report the prerequisite instead of downloading or replacing it.
  2. Inspect the current state with env -u LOW_DATA_ALLOW_NETWORK low-data status.
  3. Apply only the requested mode. Interpret "I'm back", "return online", or "remove airplane mode" as off, not removal of the reusable guard.

Switch modes

sh
# Inspect without a per-command override masking the saved policy.
env -u LOW_DATA_ALLOW_NETWORK low-data status

# Force protection for a flight or metered connection.
env -u LOW_DATA_ALLOW_NETWORK low-data on

# Explicitly disable protection after returning online.
env -u LOW_DATA_ALLOW_NETWORK low-data off

# Follow the native connection-cost detector.
env -u LOW_DATA_ALLOW_NETWORK low-data auto

Require these semantics: on forces protection; off explicitly disables it; auto protects constrained or expensive connections and fails closed when native status is unavailable. An unmetered connection is unprotected in auto.

Verify the result

After any change, run both checks with the override unset:

sh
env -u LOW_DATA_ALLOW_NETWORK low-data status
if env -u LOW_DATA_ALLOW_NETWORK low-data active; then
  printf 'active_exit=0 (protected)\n'
else
  active_exit=$?
  printf 'active_exit=%s\n' "$active_exit"
fi

Require active exit 0 for on and exit 1 for off. For auto, report the detected reason and the matching active state. Treat any other exit as a failed check. Do not claim success from the mode-setting command alone.

Keep changes bounded

  • Preserve the switch, guards, native detector, and unrelated settings. Use the command to change mode; do not delete the implementation or edit shell startup files to turn it off.
  • Limit protection claims to guarded Git history and bulk GitHub repository, release, and artifact downloads. Normal commits, pushes, metadata/API requests, curl, package installs, and model traffic remain allowed.
  • Do not claim whole-machine airplane mode, a firewall, or a bandwidth cap. PATH wrappers are not a network boundary. Never bypass them through absolute Git or GitHub CLI binaries, aliases, or custom hooks.
  • Allow LOW_DATA_ALLOW_NETWORK=1 command ... only for one explicitly approved command. Never export that override globally.
  • Do not pause, resume, kill, or relaunch agent, tmux, terminal, or background sessions. A mode change is not process-control authority.
  • Do not change other hosts, credentials, GitHub authentication, proxy settings, or remote repositories.

Inputs

  • Requested local operation: status, on, off, or auto.
  • Already-installed compatible low-data command and its trusted source.

Outputs

  • Saved mode, effective protected/unprotected state, and detected reason.
  • Post-change status and active exit-code proof.
  • Exact missing prerequisite or failed verification when the operation cannot complete.

Flow

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 Github Airplane Mode AI skill do?

Inspect or switch the local Git and GitHub download guard using an already-installed compatible low-data command. Use for airplane mode, flight or metered connections, returning online, or requests to enable, disable, or automatically select low-data protection on this machine.

Why use Github Airplane Mode on TypingMind?

Because you install it once and use it with any model. Github Airplane Mode 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 Github Airplane Mode in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vincentkoc/dotskills/tree/main/skills/github-airplane-mode. 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 Github Airplane Mode?

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 Github Airplane Mode?

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

Is the Github Airplane Mode AI skill free?

Yes. It is published on GitHub by vincentkoc under the MIT 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇