Cloudflared Tunnel logo

Cloudflared Tunnel

Community
antoniolg
cloudflared-tunnel

Create temporary public URLs for localhost apps using Cloudflare Quick Tunnels with tmux-based process management. Use when you need to preview a local app externally (mobile device, remote collaborator, QA), including host-allowlist fixes when a dev server blocks external hosts.

Overview

Publisherantoniolg
Repositoryagent-kit
Skill namecloudflared-tunnel
Stars
97
Forks
16
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Cloudflared Tunnel 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.
  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/antoniolg/agent-kit.git /tmp/agent-kit
mkdir -p .claude/skills
cp -r /tmp/agent-kit/skills/cloudflared-tunnel .claude/skills/cloudflared-tunnel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cloudflared Tunnel 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 Cloudflared Tunnel 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 Cloudflared Tunnel 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.

Cloudflared Tunnel

Use this skill when a user wants to expose any localhost web app to the internet quickly and temporarily.

What this skill standardizes

  • Runs app + tunnel in tmux for stability.
  • Avoids brittle background/nohup setups.
  • Handles host-allowlist blocks when a dev server enforces Host checks.
  • Gives clean start/stop/status commands.

Preconditions

Run these checks first:

bash
command -v tmux >/dev/null 2>&1 && echo "tmux ok" || echo "tmux missing"
command -v cloudflared >/dev/null 2>&1 && echo "cloudflared ok" || echo "cloudflared missing"

If cloudflared is missing on macOS:

bash
brew install cloudflared

Inputs you need

  • Project path
  • Dev server command
  • Local port

If not provided, infer from the repo (scripts/config/docs), then proceed.

Default tmux workflow

Use a stable session name (example: dev-tunnel).

  1. Start app window:
bash
cd <project-path>
tmux kill-session -t dev-tunnel 2>/dev/null || true
tmux new-session -d -s dev-tunnel -n app '<dev-command>'
  1. Start tunnel window:
bash
tmux new-window -t dev-tunnel -n tunnel 'cloudflared tunnel --url http://127.0.0.1:<port>'
  1. Read tunnel URL:
bash
sleep 6
tmux capture-pane -pt dev-tunnel:tunnel -S -160

Look for a URL ending in .trycloudflare.com.

If Vite/Astro blocks the host

Symptom in browser:

  • Blocked request. This host ("<host>.trycloudflare.com") is not allowed.

This is not Cloudflare-specific; it is a dev-server host allowlist rule. Only apply this fix when that error appears.

Fix by allowing trycloudflare hosts in the corresponding framework/server config.

Astro (astro.config.mjs)

js
vite: {
  server: {
    allowedHosts: ['.trycloudflare.com']
  }
}

Vite (vite.config.js|ts)

js
export default defineConfig({
  server: {
    allowedHosts: ['.trycloudflare.com']
  }
})

webpack-dev-server (if used)

js
module.exports = {
  devServer: {
    allowedHosts: '.trycloudflare.com'
  }
}

After editing config, restart the tmux session:

bash
tmux kill-session -t dev-tunnel
# then run the start commands again

Verification

  • App window shows server ready and listening on expected port.
  • Tunnel window shows Your quick Tunnel has been created!.
  • External URL opens from mobile network.

Shutdown and cleanup

Stop everything for this tunnel:

bash
tmux kill-session -t dev-tunnel
pkill -f 'cloudflared tunnel --url http://127.0.0.1:<port>' || true

Optional checks:

bash
lsof -nP -iTCP:<port> -sTCP:LISTEN || true
pgrep -fl 'cloudflared tunnel|astro dev|vite' || true

Notes

  • Quick Tunnel URLs are ephemeral and change each run.
  • Keep tunnel process alive while testing.
  • Most servers work without extra config; only change allowlists if blocked by host validation.
  • If allowlist is needed, prefer wildcard .trycloudflare.com to avoid per-run edits.
  • If the repo has strict conventions, keep edits minimal and revert only if requested.

References

  • references/troubleshooting.md

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 Cloudflared Tunnel AI skill do?

Create temporary public URLs for localhost apps using Cloudflare Quick Tunnels with tmux-based process management. Use when you need to preview a local app externally (mobile device, remote collaborator, QA), including host-allowlist fixes when a dev server blocks external hosts.

Why use Cloudflared Tunnel on TypingMind?

Because you install it once and use it with any model. Cloudflared Tunnel 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 Cloudflared Tunnel in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/antoniolg/agent-kit/tree/main/skills/cloudflared-tunnel. 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 Cloudflared Tunnel?

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 Cloudflared Tunnel?

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

Is the Cloudflared Tunnel AI skill free?

It is published on GitHub by antoniolg. Check the repository for licensing terms. 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 👇