Telegram arbitrum new token launch scanner

Skill 0xgetz/xi-agent-skills/telegram-bots/telegram-arbitrum-new-token-launch-scanner

Build a Telegram bot to detect new token deployments on Arbitrum, with on-chain/market data sourcing, risk/honeypot filtering, and Telegram alert delivery. Activate when the user wants to detect new token deployments on Arbitrum and get alerts in Telegram.From its SKILL.md

Install

npx -y skills add 0xgetz/xi-agent-skills --skill telegram-arbitrum-new-token-launch-scanner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.2 KB, 821 tokens by cl100k_base, as published. Nobody here has run it

Telegram Arbitrum New Token Launch Scanner

Overview

Detects newly deployed token contracts on Arbitrum, evaluates risk, and sends alerts.

Dependencies & Imports

from lib.gumloop_telegram import BotConfig, send_alert, build_alert, ScheduledBot, escape_md
import requests, os, json, time

Bot Config

config = BotConfig(bot_token=os.environ["TELEGRAM_BOT_TOKEN"], chat_id=os.environ["TELEGRAM_CHAT_ID"])

Core Detection

RPC = "https://arb1.arbitrum.io/rpc"
EXPLORER = "https://arbiscan.io"

def fetch_new_tokens():
    url = f"https://api.dexscreener.com/token-pairs/v1/42161"
    pairs = requests.get(url, timeout=15).json()
    cutoff = time.time() - 1800
    fresh = []
    for p in pairs:
        created = p.get("pairCreatedAt", 0) / 1000
        if created > cutoff and float(p.get("liquidity", {"usd": 0})["usd"]) > 500:
            fresh.append(p)
    return fresh

def quick_risk(token):
    payload = {"jsonrpc": "2.0", "method": "eth_call",
        "params": [{"to": token, "data": "0x70a082310000000000000000000000000000000000000000000000000000000000000001"}, "latest"], "id": 1}
    try:
        resp = requests.post(RPC, json=payload, timeout=10)
        return resp.json().get("result") is not None
    except:
        return False

def run():
    for t in fetch_new_tokens():
        if not quick_risk(t["baseToken"]["address"]):
            continue
        msg = (
            f"🚀 *New Token:* {escape_md(t['baseToken']['symbol'])}\n"
            f"💰 ${t['priceUsd']}\n"
            f"💧 Liq: ${float(t['liquidity']['usd']):,.0f}\n"
            f"🔗 [Explorer]({EXPLORER}/address/{t['baseToken']['address']})"
        )
        send_alert(config, msg)

Webhook Mode

from flask import Flask, request
app = Flask(__name__)
@app.route("/webhook/token-launch", methods=["POST"])
def webhook():
    send_alert(config, f"🚀 New token: {request.json.get('tokenAddress','')}")
    return "ok", 200

Polling (ScheduledBot)

bot = ScheduledBot(config, interval=120)
@bot.on_poll
def scan():
    run()

Docker

FROM python:3.11-slim
WORKDIR /app
RUN pip install lib-gumloop-telegram requests flask
COPY bot.py .
CMD ["python", "bot.py"]

docker build -t tg-arb-newtoken .
docker run -d -e TELEGRAM_BOT_TOKEN=x -e TELEGRAM_CHAT_ID=y tg-arb-newtoken

Production Deployment

Platform	Instructions
Railway	`railway init`, set env vars, `railway up`
Fly.io	`fly launch`, `fly secrets set TELEGRAM_BOT_TOKEN=...`
Render	Connect GitHub, add env vars, select Worker

Risk Filters

Minimum liquidity: $500 USD
Age filter: < 30 minutes
Honeypot check via eth_call before alerting
Holder count > 5 required
Reject tokens with mint() or blacklist() signature

Disclaimer

High-risk. No profit guaranteed. Not financial advice.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most product growth skills give in 821 tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07

Read product marketing context before asking questionsin 24 of 728, across 18 files
Define the ideal customer profilein 21 of 728, across 3 files
Document a rollback plan before deploymentin 21 of 728, across 12 files
Analyze the codebase to understand the productin 19 of 728, across 1 file
Ask clarifying questions about the value propositionin 19 of 728, across 1 file
Search for companies matching the criteriain 19 of 728, across 1 file
Look for signals of immediate needin 19 of 728, across 1 file
Assign a fit score from one to tenin 19 of 728, across 1 file
Identify the target decision-maker rolein 19 of 728, across 1 file
Suggest a personalized contact strategyin 19 of 728, across 1 file
Provide conversation starters for outreachin 19 of 728, across 1 file
Format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

Detect new Arbitrum token deployments
Filter tokens with liquidity below 500 USD
Filter tokens older than 30 minutes
Check for honeypots via eth_call
Require token holder count above 5
Reject tokens with mint or blacklist signatures

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.