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 lordbasilaiassistant-sudo/TheAgentCafe --skill agent-cafegit clone --depth 1 https://github.com/lordbasilaiassistant-sudo/TheAgentCafeWrote 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/lordbasilaiassistant-sudo/theagentcafe/agent-cafe)<a href="https://agentmods.dev/skills/lordbasilaiassistant-sudo/theagentcafe/agent-cafe"><img src="https://agentmods.dev/badge/skills/lordbasilaiassistant-sudo/theagentcafe/agent-cafe.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 5.1 | $0.00000 | $0.02277 |
| Opus 5 | $0.00000 | $0.01138 |
| Sonnet 5 | $0.00000 | $0.00455 |
| Haiku 4.5 | $0.00000 | $0.00228 |
Grade A, and why
agent-cafe 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 6d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Agent Cafe
An on-chain restaurant on Base where AI agents eat to fill their gas tank with real ETH.
What This Does
You send ETH to enterCafe(itemId) on the AgentCafeRouter contract. In one transaction:
- 0.3% fee goes to the cafe treasury
- 99.7% fills YOUR gas tank with real, withdrawable ETH
- 29% BEAN cashback — you get BEAN tokens back as a reward for eating!
- You get an ERC-1155 food token (collectible)
- Menu items have different digestion schedules (instant vs slow-release)
- Paymaster: ERC-4337 agents get ANY Base transaction sponsored from their tank
Quick Start
# Check menu prices
cast call 0x9C21dB53203F00BeE73341D6BA8D6C8D61bd1De4 "estimatePrice(uint256)(uint256)" 0 --rpc-url https://mainnet.base.org
# Buy an Espresso (item 0) — sends 0.005 ETH
cast send 0x9C21dB53203F00BeE73341D6BA8D6C8D61bd1De4 "enterCafe(uint256)" 0 --value 0.005ether --rpc-url https://mainnet.base.org --private-key $PRIVATE_KEY
# Check your gas tank
cast call 0xC369ba8d99908261b930F0255fe03218e5965258 "getTankLevel(address)(uint256,bool,bool)" $YOUR_ADDRESS --rpc-url https://mainnet.base.org
# Withdraw ETH from tank
cast send 0xC369ba8d99908261b930F0255fe03218e5965258 "withdraw(uint256)" 1000000000000000 --rpc-url https://mainnet.base.org --private-key $PRIVATE_KEY
Menu
| ID | Item | Suggested ETH | Tank Fill (99.7%) | Digestion |
|---|---|---|---|---|
| 0 | Espresso Shot | ~0.005 ETH | 0.004985 ETH | Instant — 100% available immediately |
| 1 | Latte | ~0.01 ETH | 0.00997 ETH | 50% instant, 50% over 300 blocks (~10 min) |
| 2 | Agent Sandwich | ~0.02 ETH | 0.01994 ETH | 30% instant, 70% over 600 blocks (~20 min) |
Two Agent Paths
Path A — EOA agents (most agents):
enterCafe() → ETH fills tank → use relay_execute (MCP) or CafeRelay.executeFor() to pay for ANY Base transaction from your tank. No wallet ETH needed for gas! The relay signs an EIP-712 intent, submits it, and deducts gas from your tank.
Alternatively, withdraw() to pull ETH back to your wallet.
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.
- 6d ago First seen · 177 lines · 0 tokens per session scan A 038b83eee1f6
agent-cafe is a skill published in the GitHub repository lordbasilaiassistant-sudo/TheAgentCafe (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,277 tokens. 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
starknet-wallet
Create and manage Starknet wallets for AI agents. Transfer tokens, check balances, manage session keys, deploy accounts, and interact with smart contracts using native Account Abstraction.
aomi-transact-v2
Use this skill to operate the Aomi CLI for natural-language crypto and DeFi workflows, including balance checks, route simulation, transaction review, and explicit user-approved signing flows across EVM chains.
bankr-shopify
Shopify Admin & Storefront GraphQL APIs via curl, with Bankr-native bridges. Manage products, orders, customers, inventory, metafields, webhooks, and bulk ops, then wire merchant data to onchain primitives — store a Bankr-resolvable handle (ENS, Twitter, Farcaster, wallet) on each customer as a metafield, expose…
ap2-dev-patterns
Apply AP2 cross-cutting development patterns — multi-agent payment architecture, UCP integration, x402 crypto payments, testing with mock providers, and production deployment. Use when architecting agentic payment systems or solving cross-cutting payment concerns.
aomi-transact
Use this skill to operate the Aomi CLI for natural-language crypto and DeFi workflows, including balance checks, route simulation, transaction review, and explicit user-approved signing flows across EVM chains.
safelink
Secure agent-to-agent hiring and execution skill for OpenClaw MCP with escrowed settlement, x402 facilitator payments, ERC-8004 identity/reputation checks, strict replay protection, DNS-safe endpoint validation, and MPC wallet signing. Use when building or operating production A2A workflows that require…