Solana防骗检测
solana-scam-detector
by ammkode
Detect scam tokens on Solana before you trade. Checks ticker patterns, token age, and known scam mints. Read-only — no wallet signing required.
安装
claude skill add --url https://github.com/openclaw/skills文档
Solana Scam Detector
Read-only scam detection for Solana tokens. No wallet signing required.
What It Does
- Token Age Check — Flags tokens younger than threshold
- Ticker Pattern Check — Flags fake stock tokens (META, AAPL, etc.)
- Mint Blacklist — Check against known scam mints
Read-Only
This module only reads blockchain data. It does NOT:
- ❌ Require wallet key file
- ❌ Require Telegram ID
- ❌ Store trade history
- ❌ Send any transactions
Installation
npm install @solana/web3.js
Configuration
Required: None (uses default public RPC)
Optional (agent can ask user):
RPC_URL— Custom RPC endpoint (default: public RPC)MIN_TOKEN_AGE_HOURS— Minimum hours (default: 4)
Usage
const { checkTokenSafety, isValidSolanaAddress } = require('./lib/scam_check.js');
// Validate address first
if (!isValidSolanaAddress(mint)) {
console.log('Invalid address');
return;
}
// Check token
const result = await checkTokenSafety(mint, symbol);
console.log(result);
// { safe: true, issues: [], config: {...} }
Agent Instructions
Keep it simple — this is read-only:
- Use default public RPC or ask user for their RPC URL
- Optionally ask user for MIN_TOKEN_AGE_HOURS preference
- Optionally allow user to add to BLACKLIST_EXACT / BLACKLIST_MINTS
- Never ask for wallet key, Telegram ID, or trade history
Files
lib/scam_check.js— Main detection logic (read-only)lib/config.js— Minimal config (RPC URL only)SKILL.md— This file
相关 Skills
Claude API
by anthropic
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
并行代理
by axelhu
Use when facing 2 or more independent tasks that can be worked on without shared state - dispatches parallel subagents using sessions_spawn for concurrent investigation and execution, adapted for OpenClaw
高光制作器
by bwbernardweston18
>