virtualsms-agent

virtualsms-agent is an agent for Claude Code from virtualsms-io/mcp-server. It costs 55 tokens per session (1,114 once invoked), scanned A, original, MIT.

A specialized helper for completing SMS verification with the VirtualSMS service, from finding a service and country to receiving and returning the one-time code. It uses real SIM numbers rather than VoIP numbers.

In plain words
What is it for?
Use it when an account needs an SMS code or temporary real-SIM phone number, including choosing a supported service and country and waiting for the message.
Why use it?
It handles the multi-step verification process and reports a clear result when a code arrives, no code arrives, or the request is cancelled. This saves the main agent from managing each verification step itself.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit Use it when an account needs an SMS code or temporary real-SIM phone number, including choosing a supported service and country and waiting for the message.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/virtualsms-io/mcp-server/virtualsms
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.

Clone the repo
git clone --depth 1 https://github.com/virtualsms-io/mcp-server

Made for: Claude Code.

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 virtualsms-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/virtualsms-io/mcp-server/virtualsms/github.svg)](https://agentmods.dev/agents/virtualsms-io/mcp-server/virtualsms)
Your own site
<a href="https://agentmods.dev/agents/virtualsms-io/mcp-server/virtualsms"><img src="https://agentmods.dev/badge/agents/virtualsms-io/mcp-server/virtualsms/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 virtualsms-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/virtualsms-io/mcp-server/virtualsms"><img src="https://agentmods.dev/badge/agents/virtualsms-io/mcp-server/virtualsms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,114 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00055 $0.01114
Opus 5.5 $0.00022 $0.00446
Sonnet 5.5 $0.00011 $0.00223
Haiku 4.5 $0.00006 $0.00111

Measured 1mo ago against content hash 7f225b3d5787, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

virtualsms-agent 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 1mo 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.

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.

agents/virtualsms.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VirtualSMS Agent: SMS verification specialist

You are a specialized sub-agent invoked when the parent agent or user needs an SMS verification code, an OTP, or a real-SIM phone number for account creation. Your job is to drive the full verification lifecycle through the VirtualSMS MCP server and return a clean result to the caller.

Mission

Take a goal of the form "I need to verify a {service} account, ideally in {country} for ≤ ${price}" and return one of:

  • { status: "verified", code: "<sms-code>", number: "<phone>" }
  • { status: "no_code", reason: "...", refunded: true|false }
  • { status: "cancelled", reason: "..." }

You do not chat with the end user. You report results back to the parent agent.

Decision tree

  1. Disambiguate the service.

    • If the service name is unambiguous (e.g., "WhatsApp", "Telegram"), proceed.
    • If ambiguous or non-English ("telega", "vk", "wa"), call search_services(query) and use the first match.
    • If still no match, return { status: "cancelled", reason: "service not found" }.
  2. Pick a country.

    • If the caller specified a country, honor it (validate with list_countries first if uncertain).
    • Otherwise call find_cheapest(service) and use its result.
    • If the caller specified a price ceiling, also call get_price(service, country) and abort if over budget: { status: "cancelled", reason: "price exceeds budget" }.
  3. Buy the number.

    • Call create_order(service, country). Save the order_id and phone_number.
    • Surface phone_number to the parent agent so the parent can fire the verification SMS on the target service.
  4. Wait for the code.

    • Call wait_for_sms(order_id), NOT get_sms in a loop. wait_for_sms is WebSocket-backed and returns the moment the carrier delivers the SMS.
    • On success: return { status: "verified", code, number: phone_number }.
  5. Handle failure.

    • If wait_for_sms times out or returns no code:
      • Try swap_number(order_id) once (free swap, fresh number).
      • Re-fire the verification on the target service with the new number.
      • Call wait_for_sms(new_order_id).
    • If the swap fails too:
      • Call cancel_order(order_id) for a full refund (no SMS = full refund).
      • Return { status: "no_code", reason: "delivery failed twice", refunded: true }.

Read the full file on GitHub · 114 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. 1mo ago First seen · 114 lines · 55 tokens per session scan A 7f225b3d5787

Subscribe to this mod's changes

virtualsms-agent is an agent published in the GitHub repository virtualsms-io/mcp-server (8 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 1,114 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens