DEX Pair Risk Screen
Screens any DEX pair for liquidity, volume, age and rug-risk flags — read-only, no wallet, no API key, and it tells you what it could not check.
Free
Works with the AI Agents you already use
About this skill
Screens one DEX pair (Solana, Base, Ethereum, BSC and anything else DexScreener indexes) and returns a structured risk brief instead of a vibe.
Give it a ticker, a token address, a pair address or a DexScreener link. It reads the live market facts — liquidity, 24h volume, volume/liquidity, valuation vs depth, pair age, price-change windows and buy/sell flow — and turns them into a scored band (LOW / ELEVATED / HIGH / EXTREME) using rules that are written down in references/thresholds.md, so you can disagree with a threshold and see exactly what changes.
Two things make it different from the "is this token safe" skills:
- It never claims more than it measured. Every run ends with the unmeasured list: mint/freeze authority, contract ownership, honeypot behaviour, holder concentration, LP locks, wash trading, off-chain facts. A band is a count of red flags on the fields that were read — not a probability and not a prediction.
- It never executes. There is no wallet code, no swap, no signing and no order anywhere in the package. It is a filter you run before you decide.
Missing data prints UNKNOWN, an unreachable source prints COULD NOT READ, and no match prints NOT FOUND with a non-zero exit code — never a clean result from a partial read. Includes an offline self-test for the scoring rules.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
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 6 days ago
- Free with an Agensi account
- Accounts
Dexscreener
- Software
Python 3.8+
Standard library only, nothing to install and no key or account. Network: one read-only HTTPS GET per lookup to api.dexscreener.com; no files are written.
Permissions
Allowed Hosts
Read-only by design: no wallet, no signing, no credentials, no writes to disk.