- Home
- Skills
- Web3 & Crypto
- Crypto Pre-Transaction Check: Sign, Pay, Token Safety
Crypto Pre-Transaction Check: Sign, Pay, Token Safety
**Crypto Pre-Transaction Check** runs before any wallet action and gives one answer: **go**, **caution** or **stop**, with the reasons in plain English.
Free
Works with the AI Agents you already use
Crypto Pre-Transaction Check: Sign, Pay, Token Safety
Example session with this skill installed
"A dApp wants me to sign this USDC permit on Base (spender 0x2222…2222, value = max uint256, deadline 99999999999). Is it safe?"
"Pay 50 USDC to 0x098B716B8Aaf21512996dC57EB0615e2383E2f96 on Ethereum."
"Is BRETT on Base (0x532f27101965dd16442E59d40670FaF5eBB142E4) OK to buy?"
- Read your context and instructions
- Compiled the crypto pre-transaction check
Real outputs from the free previews, 10/30/2026.
SignCheck free preview
- verdict: DANGER, risk_score 70, action erc2612_permit_signature
- summary: "Sign an off-chain permit: let 0x2222…2222 spend UNLIMITED USDC of USD Coin from 0x1111…1111 until never"
- flags: UNLIMITED_APPROVAL (high), OFFCHAIN_APPROVAL (medium), NO_EXPIRY (medium)
Agent: "Decision: STOP. This permit lets the spender take all your USDC with no expiry. Ask the dApp for an exact amount and a deadline."
CounterpartyCheck free preview: verdict block, confidence high, kind eoa, signals: sanctions_list_match, sources_failed: none.
PayGuard free preview: sanctioned true, match_count 1, list updated 2026-10-28.
Agent: "Decision: STOP. This address is on the US Treasury OFAC SDN list. I won't prepare this payment."
TokenVerdict free preview: verdict SAFE, score 95, confidence medium, degraded true, 0 danger and 0 warning flags, liquidity about $2.07M, sellable true.
Agent: "Decision: CAUTION. No risk signal found and the sell simulation passed, but some data was unavailable (degraded), so confidence is medium. This isn't financial advice."
Connects securely to your tools. The creator never sees your data.
About this skill
Crypto Pre-Transaction Check runs before any wallet action and gives one answer: go, caution or stop, with the reasons in plain English.
It picks the right checks for the action:
- SignCheck: what is about to be signed. Decodes a transaction, an EIP-712 request (Permit, Permit2, EIP-3009, Seaport), an EIP-7702 delegation or an x402 payment. Returns SAFE / CAUTION / DANGER, a 0-100 risk score, a one-line summary ("Approve 0x3c1A…8d6F to spend UNLIMITED USDC from your wallet") and flags such as unlimited approvals, off-chain approvals and no expiry.
- CounterpartyCheck: who gets paid or approved. For an EVM (Base, Ethereum, Polygon, Arbitrum One) or Solana address and an intent (pay, approve or interact): ok / caution / block, confidence, wallet vs contract, sanctions and scam-list signals, and whether it's a known x402 payee.
- PayGuard: sanctions screening on any chain. Is the address on the US Treasury OFAC SDN list of digital currency addresses? Exact match, any chain.
- TokenVerdict: Base ERC-20 tokens. A simulated buy, transfer and sell (honeypot, buy/sell tax), owner powers (mint, blacklist, pause, upgradeable, renounced), liquidity and LP burn, holder concentration, verified source and age.
- SolVerdict: Solana SPL and Token-2022 tokens. Mint and freeze authority, Token-2022 extensions that can block or tax sells (permanent delegate, transfer hook, transfer fee, default-frozen, pausable), metadata mutability, liquidity, holder concentration and age. Never SAFE on incomplete data.
Free by default. Every check uses the tools' free previews (verdict, score and counts) and free remote MCP servers (PayGuard: 30 full screenings a day). Detailed reasons and evidence are in optional paid tiers, pay per call in USDC over x402: SignCheck $0.005 / $0.015, CounterpartyCheck $0.005 / $0.015 / $0.05, PayGuard $0.001 per address, TokenVerdict $0.005 to $0.05, SolVerdict $0.005 / $0.02. The skill never pays without your explicit approval.
Where it stops. It never signs, sends or holds anything. It's a safety check, not financial, legal or investment advice: "ok" or "SAFE" means no known risk signal was found, not that a counterparty or token is trustworthy, and a token that passes can be changed later by whoever controls it. TokenVerdict covers Base mainnet only. A failed or rate-limited check is reported as "not run", never as clean.
SignCheck, CounterpartyCheck, PayGuard, TokenVerdict and SolVerdict are built and operated by the youraitools.co team: https://youraitools.co/built-by-us?utm_source=agensi&utm_medium=skill&utm_campaign=crypto-pretx-check
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Web3 & Crypto.
- Free previews return verdicts, scores and counts; full reasons and evidence are paid tiers.
- Not financial, legal or investment advice; not an audit; no guarantee.
- TokenVerdict is Base mainnet only. SignCheck on-chain facts cover Base, Ethereum and Base Sepolia.
- PayGuard checks the OFAC SDN address list only: exact matches, no other sanctions lists, no exposure analysis.
- Free previews are rate-limited per IP (about 10 a minute on most).
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 17 days ago
- Free with an Agensi account
- Accounts
Youraitools
Permissions
Allowed Hosts