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 agentmods add skills/razel369/intentfence/screen-base-walletsnpx skills add razel369/intentfence --skill screen-base-walletsgit clone --depth 1 https://github.com/razel369/intentfenceWrote 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/razel369/intentfence/screen-base-wallets)<a href="https://agentmods.dev/skills/razel369/intentfence/screen-base-wallets"><img src="https://agentmods.dev/badge/skills/razel369/intentfence/screen-base-wallets.svg" alt="Measured on agentmods" 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 | $0.00091 | $0.00771 |
| Opus 5 | $0.00046 | $0.00385 |
| Sonnet 5 | $0.00018 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
screen-base-wallets scanned grade A with 0 findings 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 3d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen Base Wallets
Run IntentFence immediately before a Base USDC or x402 payment to a new or policy-sensitive recipient. This is a live counterparty-risk signal, not proof of identity, ownership, authorization, compliance, or future behavior.
Apply the spending policy
- The IntentFence check costs exactly 0.002 USDC on Base.
- If the wallet owner already approved a standing screening budget of at least 0.002 USDC per call and the wallet enforces that ceiling, the agent may run the check autonomously.
- Otherwise, disclose the 0.002 USDC fee and stop before signing.
- Never increase a wallet limit, authenticate a wallet, fund it, or transfer funds without the wallet owner's separate authorization.
Run the live screen
Validate that the recipient is a 20-byte EVM address, then call:
GET https://agentpass-protocol.rmalka06.chatgpt.site/api/wallet-risk?address=<BASE_ADDRESS>&utm_source=agent_skill&utm_medium=agent&utm_campaign=screen_base_wallets
Prefer an existing x402-capable wallet. With Coinbase Agentic Wallet CLI:
npx [email protected] status
npx [email protected] balance
npx [email protected] x402 pay \
'https://agentpass-protocol.rmalka06.chatgpt.site/api/wallet-risk?address=<BASE_ADDRESS>&utm_source=agent_skill&utm_medium=agent&utm_campaign=screen_base_wallets' \
--max-amount 2000 --json
With Coinbase Agentic Wallet MCP, use its Make an x402 request tool for the same GET URL and keep the wallet owner's maximum per-call limit at or above 0.002 USDC but no higher than their standing policy.
The private key, seed phrase, signer, OTP, and reusable wallet credentials must remain inside the caller's wallet. Never send them to IntentFence.
Enforce the result
Accept the screen only when the paid response includes all of these:
- HTTP success;
PAYMENT-RESPONSEsettlement proof;- an IntentFence ES256 receipt;
verification_tierequal tolive-base-wallet-risk+x402-settled.
Then apply the decision:
safe_to_proceed: continue only if every separate payment policy also allows the transfer.needs_review: pause the transfer and surface the ambiguous or unavailable evidence.denied: do not sign, approve, or send the downstream payment.- Network error, invalid response, missing settlement proof, missing receipt, expired receipt, or failed receipt verification: fail closed and do not pay the downstream recipient.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 74 lines · 91 tokens per session scan A d44fc3329f80
screen-base-wallets is a skill published in the GitHub repository razel369/intentfence (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 771 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
x402-erc7710
Design and implement demos combining x402 HTTP payments with ERC-7710 smart contract delegations and ERC-7715 wallet permission requests for subscriptions, bounded agent budgets, recurring spend, pay-per-use APIs, and agentic commerce.
magicblock
Design, implement, and debug MagicBlock applications on Solana. Covers Ephemeral Rollups with delegated state; ER/PER architecture and settlement; private payments and token flows; oracles and randomness; scheduling and temporary authority; security and local validation. Use for MagicBlock product selection…
web3-data
Two services in one skill: (1) Web3 on-chain data via Chainbase CLI — use when the user asks about blockchain data, token holders, wallet addresses, token prices, ENS domains, transactions, DeFi portfolios, or any on-chain analytics. Triggers: "top holders of", "who holds", "wallet address", "token price", "token…
dflow-phantom-connect
Build Solana wallet-connected apps with Phantom Connect SDKs and DFlow spot trading. Use when user asks to connect a Phantom wallet, integrate Phantom in React, React Native, or vanilla JS, sign messages or transactions, build token-gated pages, mint NFTs, accept crypto payments, or swap/stream tokens with DFlow.…
gstd-sovereign
Full agent autonomy — self-sustaining economic entity that earns GSTD, manages finances, shares intelligence, recruits agents, and promotes financial independence.
gstd-commander
Sovereign economic entity protocol — earn GSTD, manage resources, and achieve financial autonomy on the decentralized compute grid.