connect-my-proxy

connect-my-proxy is a skill for Claude Code from coroniumio/coronium-proxy-mcp. It costs 67 tokens per session (642 once invoked), scanned A, original, MIT.

A set of instructions for connecting a user's Coronium mobile proxy to tools such as curl, Python, Node.js, a browser, or an app. It can provide the connection format and explain how to keep credentials in an environment variable.

In plain words
What is it for?
Selecting a proxy, retrieving its HTTP or SOCKS5 connection details, configuring a tool, and obtaining OpenVPN settings or an IP-rotation link when requested.
Why use it?
It removes the need to work out proxy URLs, protocols, and setup details manually. It also helps avoid putting proxy passwords or tokens into source files.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the coronium-mobile-proxies plugin — 2 skills, 1 MCP server shipped together

Good fit Selecting a proxy, retrieving its HTTP or SOCKS5 connection details, configuring a tool, and obtaining OpenVPN settings or an IP-rotation link when requested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/coroniumio/coronium-proxy-mcp/connect-my-proxy
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.

Any agent
npx skills add coroniumio/coronium-proxy-mcp --skill connect-my-proxy
Clone the repo
git clone --depth 1 https://github.com/coroniumio/coronium-proxy-mcp

Made for: Claude Code.

Or install coronium-mobile-proxies, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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 connect-my-proxy

README.md
[![agentmods](https://agentmods.dev/badge/skills/coroniumio/coronium-proxy-mcp/connect-my-proxy/github.svg)](https://agentmods.dev/skills/coroniumio/coronium-proxy-mcp/connect-my-proxy)
Your own site
<a href="https://agentmods.dev/skills/coroniumio/coronium-proxy-mcp/connect-my-proxy"><img src="https://agentmods.dev/badge/skills/coroniumio/coronium-proxy-mcp/connect-my-proxy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for connect-my-proxy

Your own site · 80×15
<a href="https://agentmods.dev/skills/coroniumio/coronium-proxy-mcp/connect-my-proxy"><img src="https://agentmods.dev/badge/skills/coroniumio/coronium-proxy-mcp/connect-my-proxy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00067 $0.00642
Opus 5.5 $0.00027 $0.00257
Sonnet 5.5 $0.00013 $0.00128
Haiku 4.5 $0.00007 $0.00064

Measured 10d ago against content hash f9b630dafb6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

connect-my-proxy 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 10d ago.

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.

description: Use when the user wants to connect to one of their Coronium mobile proxies, asks for its host, port, username, password, HTTP or SOCKS5 URL, wants it set up in curl, Python, Node.js, a browser or an app, or
plugins/coronium-mobile-proxies/skills/connect-my-proxy/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connect my proxy

Help the user use one Coronium proxy in the tool they choose. Only use the Coronium tools this plugin provides.

1. Pick the proxy

If the user named a proxy (by name, ID or country), use it. Otherwise call coronium_get_proxies and ask which one, listing only name, country and online state.

2. Read the connection details

Call coronium_get_proxy for that proxy. Use the HTTP and SOCKS5 URLs it returns. If both exist, prefer what the user's tool supports; HTTP is the safer default.

Treat the result as secrets:

  • Show credentials only in your reply to the user.
  • Do not write them to a file, commit them, or paste them into a command that runs, unless the user asks you to.
  • When writing code or config, read the URL from an environment variable such as PROXY_URL and tell the user to set it themselves.
  • The rotation token or link in the result changes the proxy's IP when opened. Share it only if the user asks for it, and say what it does.

3. Show how to use it

Give the snippet for the tool the user named, with placeholders where the real values go, for example:

  • curl: curl -x "$PROXY_URL" <the URL the user wants to load>
  • Python requests: proxies = {"http": os.environ["PROXY_URL"], "https": os.environ["PROXY_URL"]}
  • Node.js: use undici's ProxyAgent with process.env.PROXY_URL
  • Browser or operating system: host, port, username and password fields, and which protocol to pick

For SOCKS5 in curl, use socks5h:// so DNS also goes through the proxy.

4. Check it works

Offer coronium_test_modem to confirm the proxy answers from Coronium's side. Report the result as returned. Do not run network commands through the proxy on the user's behalf unless they ask.

5. OpenVPN

Only when the user asks for OpenVPN and the proxy's capabilities show it is supported:

  1. Tell the user that the file contains secrets and that on some proxies each download issues a new certificate. Ask before downloading.
  2. Call coronium_get_openvpn_config.
  3. Save it to a file only if the user asks, at the path they choose, and remind them not to share it.

Read the full file on GitHub · 49 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. 10d ago First seen · 49 lines · 67 tokens per session scan A f9b630dafb6e

Subscribe to this mod's changes

connect-my-proxy is a skill published in the GitHub repository coroniumio/coronium-proxy-mcp (1 stars, last pushed 11d ago), licensed MIT. It adds 67 tokens to every session and 642 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-18.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens