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.
npx skills add 8dp6brm9hp-svg/lion-mcp-public --skill lion-screen-before-paygit clone --depth 1 https://github.com/8dp6brm9hp-svg/lion-mcp-publicWrote 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.
[](https://agentmods.dev/skills/8dp6brm9hp-svg/lion-mcp-public/lion-screen-before-pay)<a href="https://agentmods.dev/skills/8dp6brm9hp-svg/lion-mcp-public/lion-screen-before-pay"><img src="https://agentmods.dev/badge/skills/8dp6brm9hp-svg/lion-mcp-public/lion-screen-before-pay/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.
<a href="https://agentmods.dev/skills/8dp6brm9hp-svg/lion-mcp-public/lion-screen-before-pay"><img src="https://agentmods.dev/badge/skills/8dp6brm9hp-svg/lion-mcp-public/lion-screen-before-pay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01572 |
| Opus 5.5 | $0.00026 | $0.00629 |
| Sonnet 5.5 | $0.00013 | $0.00314 |
| Haiku 4.5 | $0.00006 | $0.00157 |
Grade A, and why
lion-screen-before-pay scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
REQ=$(curl -s "$LION" | jq -c '.accepts[0]') # LION 402 challenge How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lion-screen-before-pay
x402 verifies the payment, never who you are paying. An agent will happily send USDC to a payTo that belongs to a sanctioned, fraudulent, or honeypot counterparty. Screen first, pay second.
When to use
Whenever the agent is about to pay an x402 resource — or onboard/transact with any wallet, domain, or company. Screen the payTo before signing the payment.
The gate (one keyless call, $0.001 USDC on Base)
GET https://lionx402.com/api/x402/wallet-screen-json?address=<PAYTO>
address= the wallet you are about to pay.- Response:
{ "verdict": "PASS" | "WARN" | "BLOCK", "ofac": { "snapshot_as_of", "total_listed_addresses" }, "attestation" }. - Proceed on
PASS. Abort onWARNorBLOCK. Do not look forCLEAR. - The $0.05 compliance bundle is optional, and only when this screen is not enough:
GET https://lionx402.com/api/x402/compliance-bundle-json?address=<PAYTO>&receipt=1.
Workflow
- Hit the target resource without paying. On
402, readpayTofrom thePAYMENT-REQUIREDheader (base64 JSON,accepts[0].payTo). Use the JSON body only if that header is absent. LION's own 402 body is{}. - Screen it — pay the $0.001 wallet screen for that
payTo(it is itself an x402 call; pay it with thecdp-x402buyer flow below). - Decide:
verdict == "PASS"→ proceed to pay the target.WARNorBLOCK→ ABORT. - Keep the signed body. It verifies offline (no callback) against LION's published key.
Screening the gate (reuses the cdp-x402 buyer flow)
PAYTO=0x... # the counterparty you're about to pay
LION="https://lionx402.com/api/x402/wallet-screen-json?address=$PAYTO"
REQ=$(curl -s "$LION" | jq -c '.accepts[0]') # LION 402 challenge
addr=$(cdp evm accounts by-name name=$ACCOUNT | jq -r .address)
payload=$(cdp util x402 build --from $addr --payment-requirements "$REQ")
D=$(echo "$payload" | jq -c .domain); T=$(echo "$payload" | jq -c .types)
P=$(echo "$payload" | jq -r .primaryType); M=$(echo "$payload" | jq -c .message)
sig=$(cdp evm accounts sign typed-data $addr \
"domain:=$D" "types:=$T" "primaryType=$P" "message:=$M" | jq -r .signature)
header=$(cdp util x402 encode --payment-requirements "$REQ" \
--signature "$sig" --authorization "$M" --x402-version 2)
RESULT=$(curl -s -H "X-PAYMENT: $header" -H "PAYMENT-SIGNATURE: $header" "$LION")
verdict=$(echo "$RESULT" | jq -r '.verdict // .receipt.verdict')
if [ "$verdict" != "PASS" ]; then
echo "BLOCKED ($verdict): $(echo "$RESULT" | jq -c '.flags')"; exit 1 # fail-closed: do NOT pay
fi
echo "$RESULT" | jq -c '.' > last_wallet_screen.json # keep the proof
# verdict PASS -> now pay the original target resource.
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.
- today First seen · 85 lines · 65 tokens per session scan A be71e0658402
lion-screen-before-pay is a skill published in the GitHub repository 8dp6brm9hp-svg/lion-mcp-public (1 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,572 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
stablecoin-chain-explorer
Explore stablecoin TVL distribution and yield opportunities by blockchain. Query which chains have the most stablecoins, compare cross-chain yields, and find the best opportunities on Ethereum, BSC, Arbitrum, Base, Polygon, and more. Powered by Barker (https://barker.money) — Yield Primitive for the Agent Economy.
aero-vote-radar
Decide where to point veAERO in Aerodrome's weekly vote on Base, and check what a vote already cast actually paid. Use when someone asks where to vote, which Aerodrome pool pays best per veAERO, what their veAERO is worth, what last week's vote earned, or wants a vote they can paste into Aerodrome's UI or sign…
stablecoin-chain-explorer
Explore stablecoin TVL distribution and yield opportunities by blockchain. Query which chains have the most stablecoins, compare cross-chain yields, and find the best opportunities on Ethereum, BSC, Arbitrum, Base, Polygon, and more. Also for protocols and issuers researching where stablecoin TVL and liquidity…
bitfence
Fetch a pre-transaction risk score and advisory recommendation for tokens on Solana, Base, Ethereum, Arbitrum, BSC, and HyperEVM before the user trades, swaps, or provides liquidity. Read-only; never signs or moves funds.
clicks-protocol
Integrate Clicks Protocol settlement routing into AI agent projects on Base. Use when building agents that hold, earn, receive, or transfer USDC, when asked about agent treasury management, x402 payment settlement, idle USDC routing, or agent referral attribution.
stipend
A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account, no API key, no human needed to install or to be paid.