cloudflared

A tool for creating a temporary public web address that forwards to an app running on your computer. Cloudflared is the command-line program that creates this connection through Cloudflare.

In plain words
What is it for?
Use it to share a sandbox or development app publicly, with an optional stable hostname or access policy when needed.
Why use it?
It lets other people open a local preview without deploying the app to a server. It also helps avoid exposing the wrong local service by checking which port should be shared.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mifunedev/openharness/cloudflared
Any agent
npx skills add mifunedev/openharness --skill cloudflared
Clone the repo
git clone --depth 1 https://github.com/mifunedev/openharness

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00095 $0.01711
Opus 5 $0.00048 $0.00856
Sonnet 5 $0.00019 $0.00342
Haiku 4.5 $0.00010 $0.00171

Measured 2d ago against content hash 9ec1afc1cacd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloudflared scanned grade A with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

script's local `curl` precheck is necessary but NOT sufficient: an origin can
.oh/skills/cloudflared/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloudflared

Use Cloudflared as the default public tunnel for sandbox app previews. Prefer a Cloudflare quick tunnel for temporary sharing; use a named tunnel only when the operator explicitly needs a stable hostname or Cloudflare Access policy.

Arguments

Arguments received: $ARGUMENTS

  • PORT: first positional argument; required (example: 3000)
  • --host: local upstream host; default 127.0.0.1
  • --name: optional slug for the tmux/log suffix; default is the port
  • --session: optional tmux session name override; default cloudflared-<slug>

If PORT is missing, ask which local port to tunnel.

Pre-flight — confirm the public surface (do NOT assume)

A dev stack usually listens on several ports where only ONE is the intended public surface (e.g. a web UI on :3005, a browser-editor gateway on :8788, a metrics port, a DB). Picking the wrong one wastes a tunnel and can expose the wrong service.

Before starting a tunnel:

  1. If the caller did not name the service explicitly, list the listening ports and ask which service is meant to be public — never default to "the web port". ss -ltnp or the project's dev docs disambiguate.
  2. A quick-tunnel URL is a public bearer URL — anyone with it reaches the origin. If the target is not a throwaway static preview (it has auth, webhooks, an admin surface, or real data), get an explicit go-ahead before exposing it.

Quick tunnel flow

Run inside the sandbox, after the app is already listening locally:

bash "$CLAUDE_SKILL_DIR/scripts/run.sh" $ARGUMENTS

The script verifies cloudflared, tmux, and the local upstream, starts a Cloudflare quick tunnel in tmux, waits for the generated URL, and prints inspect/log/stop commands.

Always verify through the PUBLIC url, not just the local upstream. The script's local curl precheck is necessary but NOT sufficient: an origin can answer 127.0.0.1 fine yet return 404/421 through the tunnel because it routes on (or rejects) the Host header the tunnel sends (see Troubleshooting). After the URL appears:

Read the full file on GitHub · 157 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 157 lines · 95 tokens per session scan A 9ec1afc1cacd

Subscribe to this mod's changes

cloudflared is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,711 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across…

vercel-labs/agent-browser · 126 tokens

protected-vercel-deployments

Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection with agent-browser. Use when a preview or production URL redirects to a Vercel login page, returns a protection 401 or 403, or needs short-lived Trusted Sources OIDC authentication instead of a static bypass secret or…

vercel-labs/agent-browser · 75 tokens

cuml-machine-learning

Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.

langchain-ai/deepagents · 43 tokens

blog-post

Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.

langchain-ai/deepagents · 58 tokens

social-media

Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.

langchain-ai/deepagents · 58 tokens

remember

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…

langchain-ai/deepagents · 71 tokens