grizzly_sms

grizzly_sms is a skill for Claude Code, Codex from GrizzlySMS-Git/grizzly-sms-mcp. It costs 15 tokens per session (1,244 once invoked), scanned A, a copy of grizzly_sms, MIT.

A skill for renting virtual phone numbers and using SMS verification through the Grizzly SMS service.

In plain words
What is it for?
Checking balances and prices, choosing countries and services, renting numbers, and receiving SMS verification codes.
Why use it?
It provides a documented way to handle verification codes and related account or service requests.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Checking balances and prices, choosing countries and services, renting numbers, and receiving SMS verification codes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/grizzlysms-git/grizzly-sms-mcp/grizzly-sms-skill
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 GrizzlySMS-Git/grizzly-sms-mcp --skill grizzly-sms-skill
Clone the repo
git clone --depth 1 https://github.com/GrizzlySMS-Git/grizzly-sms-mcp

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 grizzly_sms

README.md
[![agentmods](https://agentmods.dev/badge/skills/grizzlysms-git/grizzly-sms-mcp/grizzly-sms-skill/github.svg)](https://agentmods.dev/skills/grizzlysms-git/grizzly-sms-mcp/grizzly-sms-skill)
Your own site
<a href="https://agentmods.dev/skills/grizzlysms-git/grizzly-sms-mcp/grizzly-sms-skill"><img src="https://agentmods.dev/badge/skills/grizzlysms-git/grizzly-sms-mcp/grizzly-sms-skill/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 grizzly_sms

Your own site · 80×15
<a href="https://agentmods.dev/skills/grizzlysms-git/grizzly-sms-mcp/grizzly-sms-skill"><img src="https://agentmods.dev/badge/skills/grizzlysms-git/grizzly-sms-mcp/grizzly-sms-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,244 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 88% copy Near-identical to another mod 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 $0.00015 $0.01244
Opus 5 $0.00008 $0.00622
Sonnet 5 $0.00003 $0.00249
Haiku 4.5 $0.00002 $0.00124

Measured 12d ago against content hash 1e0ef578a642, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

grizzly_sms 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 12d 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.

Origin

This is a copy

88% identical to grizzly_sms — 21 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

grizzly-sms-skill/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grizzly SMS Skill

Use this skill when the user needs: SMS verification, virtual numbers (Uber, Telegram, WhatsApp, Instagram, etc.), balance, prices, countries, services, or account registration with a rented phone number.

API Key — Ask in Dialog

Before running any Grizzly command, you MUST ask the user for the API key (unless they already gave it in this conversation):

Please provide your Grizzly SMS API key. Register on grizzlysms.com, then go to the API section (grizzlysms.com/docs) and copy the key.

When the user provides the key in chat — use it immediately. Pass it via exec env on every Grizzly call. Do NOT tell the user to set environment variables or edit config. The exec tool accepts env overrides; use them.

exec(command="node {baseDir}/scripts/grizzly-cli.mjs get_services", env={"GRIZZLY_SMS_API_KEY": "<exact_key_user_sent>"})

Example: user sends e069d36075b9b230fe1eb159b86526d1 → use env={"GRIZZLY_SMS_API_KEY": "e069d36075b9b230fe1eb159b86526d1"} in exec. Then proceed with get_services, request_number, etc.

If the key is already in config (skills.entries.grizzly_sms.env), omit env. Otherwise always ask and pass via env.

DO NOT ask the user to set GRIZZLY_SMS_API_KEY in environment variables or config files when they already provided the key in chat. Use it directly.

How to Call

There is NO tool named grizzly_sms.get_services(). You MUST use the exec tool. Example:

exec(command="node {baseDir}/scripts/grizzly-cli.mjs get_services", env={"GRIZZLY_SMS_API_KEY": "<user_key>"})

Use host=gateway only if tools.exec.host is configured for gateway. OpenClaw replaces {baseDir} with the skill folder path.

Commands (run via exec)

What to do Exec command
List services (find Uber) node {baseDir}/scripts/grizzly-cli.mjs get_services
List countries (Brazil=73) node {baseDir}/scripts/grizzly-cli.mjs get_countries
Check balance node {baseDir}/scripts/grizzly-cli.mjs get_balance
Request number node {baseDir}/scripts/grizzly-cli.mjs request_number ub 73
Get SMS code node {baseDir}/scripts/grizzly-cli.mjs get_status <activationId>
Complete activation node {baseDir}/scripts/grizzly-cli.mjs set_status <activationId> 6

Read the full file on GitHub · 103 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. 12d ago First seen · 103 lines · 15 tokens per session scan A 1e0ef578a642

Subscribe to this mod's changes

grizzly_sms is a skill published in the GitHub repository GrizzlySMS-Git/grizzly-sms-mcp (15 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 1,244 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to grizzly_sms, differing in 21 lines, and is treated as a copy.

Related

Other skills, from other repositories