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.
git clone --depth 1 https://github.com/virtualsms-io/mcp-serverWrote 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.
[](https://agentmods.dev/agents/virtualsms-io/mcp-server/virtualsms)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
-
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" }.
-
Pick a country.
- If the caller specified a country, honor it (validate with
list_countriesfirst 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" }.
- If the caller specified a country, honor it (validate with
-
Buy the number.
- Call
create_order(service, country). Save theorder_idandphone_number. - Surface
phone_numberto the parent agent so the parent can fire the verification SMS on the target service.
- Call
-
Wait for the code.
- Call
wait_for_sms(order_id), NOTget_smsin a loop.wait_for_smsis WebSocket-backed and returns the moment the carrier delivers the SMS. - On success: return
{ status: "verified", code, number: phone_number }.
- Call
-
Handle failure.
- If
wait_for_smstimes 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).
- Try
- 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 }.
- Call
- If
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.
- 1mo ago First seen · 114 lines · 55 tokens per session scan A 7f225b3d5787
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.