ap-tunnels

ap-tunnels is a skill for Claude Code, Codex from agentproto/ts. It costs 69 tokens per session (807 once invoked), scanned A, original, Apache-2.0.

A tunnel tool that gives a local development server a public internet URL. It can use temporary or named Cloudflare or ngrok tunnels.

In plain words
What is it for?
Use it to publish a local port for webhook targets, share a development preview, test from a phone, or expose the agent gateway remotely.
Why use it?
Services outside your machine cannot normally reach localhost, which makes webhooks, demos, and remote testing difficult.

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/agentproto/ts/ap-tunnels
Any agent
npx skills add agentproto/ts --skill ap-tunnels
Clone the repo
git clone --depth 1 https://github.com/agentproto/ts

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ap-tunnels

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentproto/ts/ap-tunnels.svg)](https://agentmods.dev/skills/agentproto/ts/ap-tunnels)
Your own site
<a href="https://agentmods.dev/skills/agentproto/ts/ap-tunnels"><img src="https://agentmods.dev/badge/skills/agentproto/ts/ap-tunnels.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00069 $0.00807
Opus 5 $0.00034 $0.00404
Sonnet 5 $0.00014 $0.00161
Haiku 4.5 $0.00007 $0.00081

Measured today against content hash a0716815fc60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ap-tunnels scanned grade A with 0 findings 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 today.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/skill-pack-agentproto/src/skills/ap-tunnels/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ap-tunnels

When to use

  • A local dev server must be reachable from the internet (webhook targets, demo links, mobile testing).
  • You want to drive this daemon's MCP gateway from a remote client.
  • A tunnel is stuck or duplicated and needs to be found and rotated.

tunnel_*: expose any local port

// 1. Always check first — one tunnel per port; duplicates just fail
tunnel_list({ "onlyActive": true })

// 2. Quick tunnel: no account, ephemeral URL, ready in seconds
tunnel_create({ "targetPort": 3000, "provider": "cloudflare-quick", "label": "vite-preview" })
// → { "tunnelId": "uuid", "url": "https://random-words.trycloudflare.com", ... }

// 3. Named tunnel: stable hostname you provisioned once
tunnel_create({
  "targetPort": 3000,
  "provider": "cloudflare-named",
  "hostname": "app.example.com",
  "tunnelId": "11111111-2222-3333-4444-555555555555",
  "credentialsFile": "~/.cloudflared/<tunnelId>.json",
  "autostart": true
})

// 4. Inspect / stop (stop is idempotent)
tunnel_status({ "tunnelId": "uuid" })
tunnel_stop({ "tunnelId": "uuid" })

tunnel_create does NOT gate traffic with auth — it is a pure passthrough; whatever service is on targetPort handles its own authentication. list_tunnel_adapters enumerates the installed tunnel backends and their capabilities. Providers with credentials (e.g. ngrok authtokens, named-tunnel ids) are configured once, stored sensitively, and never echoed.

remote_enable: publish the gateway itself

remote_enable({ "provider": "quick" })            // bearer-gated MCP gateway, URL shown once
remote_status({})                                  // provider, public URL, createdAt — no token
remote_disable({})                                 // tear down + drop bearer auth (idempotent no-op if off)

remote_enable with no targetPort publishes this MCP gateway and gates it with a bearer token. Re-running while active errors — call remote_disable first to rotate.

Gotchas

  • Bearer token is shown ONCE at remote_enable — store it immediately; only its hash persists.
  • Quick tunnels get a NEW URL every relaunch (daemon restart, tunnel_stop/create). For anything that must survive, use a named tunnel with autostart: true.
  • tunnel_list before tunnel_create — creating a second tunnel for the same port is a silent no-op at best and a confusing duplicate at worst.
  • tunnel_stop and tunnel_status accept either the tunnel id or the friendly name set at create time.
  • A tunnel exposes the whole port, not just one route — make sure the service behind it has its own auth before sharing the URL.

Read the full file on GitHub · 65 lines

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. today First seen · 65 lines · 69 tokens per session scan A a0716815fc60

Subscribe to this mod's changes

ap-tunnels is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 807 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

aws-strands-agents-agentcore

Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability, quality evaluations, multi-agent orchestration, and MCP server integration.

sammcj/agentic-coding · 55 tokens

strands-review

Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…

strands-agents/harness-sdk · 125 tokens

pr-writer

Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.

strands-agents/harness-sdk · 39 tokens

docs-reviewer

Review documentation drafts for voice consistency, structure, and terminology before PR submission. Use after completing a draft, when checking if docs are ready to ship, or automatically after docs-writer produces output. Also triggers on "review this draft", "check my docs", "is this ready to ship", "review before…

strands-agents/harness-sdk · 68 tokens

docs-writer

Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…

strands-agents/harness-sdk · 74 tokens

docs-audit

Assess a published or in-progress documentation page for quality, accuracy, and voice compliance. Use before rewriting a page, during periodic health checks, when community signals point to confusion, or when comparing against competitor docs. Also triggers on "audit this page", "assess the docs", "what's wrong with…

strands-agents/harness-sdk · 79 tokens