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 ObolNetwork/obol-stack --skill ethereum-referencegit clone --depth 1 https://github.com/ObolNetwork/obol-stackWrote 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/obolnetwork/obol-stack/ethereum-reference)<a href="https://agentmods.dev/skills/obolnetwork/obol-stack/ethereum-reference"><img src="https://agentmods.dev/badge/skills/obolnetwork/obol-stack/ethereum-reference/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/obolnetwork/obol-stack/ethereum-reference"><img src="https://agentmods.dev/badge/skills/obolnetwork/obol-stack/ethereum-reference.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 | $0.00074 | $0.00681 |
| Opus 5.5 | $0.00030 | $0.00272 |
| Sonnet 5.5 | $0.00015 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
ethereum-reference 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 yesterday.
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.
What it actually says
Ethereum reference
Ten topics, one folder each. Read the topic's GUIDE.md only when the task needs it.
Paths inside a topic's GUIDE.md (references/…, scripts/…) are relative to that topic folder;
../<topic>/… points at a sibling topic.
| Topic | Read | When |
|---|---|---|
| Contract addresses | addresses/GUIDE.md |
Any contract address: the Stack's own rails (USDC, OBOL, Permit2, ERC-8004), stablecoins, DEXs, lending, bridges, L2-native protocols, Safe/AA/ENS, major tokens. Start with addresses/references/obol-payments.md. |
| Bridging | bridging/GUIDE.md |
Moving assets between L1 and L2s: canonical bridges, CCIP/Across, deposits, withdrawals, claims, and when not to bridge. |
| L2s | l2s/GUIDE.md |
Choosing or explaining an L2 (Arbitrum, Optimism, Base, zkSync, Scroll, Unichain, Celo, Robinhood Chain), how they settle, what runs where. |
| Gas | gas/GUIDE.md |
Current gas prices, transaction costs, fee economics, mainnet vs L2 cost. |
| Standards | standards/GUIDE.md |
ERC-20, ERC-721, ERC-1155, ERC-4337, ERC-8004 and newer standards: what they are and when each applies. |
| Building blocks | building-blocks/GUIDE.md |
DeFi legos and composability: the major protocols per chain and how they fit together. |
| Indexing | indexing/GUIDE.md |
Reading historical onchain data at scale: events, logs, The Graph, Ponder, indexing patterns. |
| Wallets | wallets/GUIDE.md |
Wallet types: EOAs, EIP-7702 smart EOAs, Safe multisig, account abstraction, keeping keys out of git. |
| Concepts | concepts/GUIDE.md |
Core mental models LLMs get wrong: contracts as state machines, incentive design, randomness, approvals, AMMs, lending, stablecoins, oracles. |
| Why Ethereum | why/GUIDE.md |
Why build on Ethereum, and the AI-agent angle: ERC-8004, x402, composability, permissionless deployment. |
Verify addresses on-chain before sending value: eth_getCode returns real bytecode and an
eth_call (e.g. symbol()) returns what you expect. In the Obol Stack, the ethereum-networks
skill's scripts/rpc.sh does both, and the inspect skill vets a contract before you sign.
What ships with it
20 files 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.
- addresses/GUIDE.md 4.8 KB
- addresses/references/agents-and-tokens.md 1.3 KB
- addresses/references/bridges.md 3.2 KB
- addresses/references/defi.md 2.9 KB
- addresses/references/dex.md 3.9 KB
- addresses/references/infrastructure.md 3.3 KB
- addresses/references/l2-native.md 6.5 KB
- addresses/references/obol-payments.md 2.6 KB
- addresses/references/robinhood-chain.md 4.5 KB
- addresses/references/stablecoins.md 1.8 KB
- addresses/references/staking.md 3.7 KB
- bridging/GUIDE.md 16 KB
- building-blocks/GUIDE.md 11 KB
- concepts/GUIDE.md 10 KB
- gas/GUIDE.md 5.4 KB
- indexing/GUIDE.md 9.9 KB
- l2s/GUIDE.md 11 KB
- standards/GUIDE.md 11 KB
- wallets/GUIDE.md 7.1 KB
- why/GUIDE.md 3.3 KB
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.
- yesterday First seen · 28 lines · 74 tokens per session scan A 07d94a3e4d02
ethereum-reference is a skill published in the GitHub repository ObolNetwork/obol-stack (11 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 681 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
ethereum-development
Production-grade Ethereum/EVM development workflow for smart contracts, dApps, transactions, clients, gas optimization, testing, security review, deployment, verification, monitoring, and incident response across Foundry, Hardhat, Solidity, TypeScript, viem, ethers, wagmi, and common EVM networks.
Web3 & Blockchain Development
Production-grade Web3 development with Solidity smart contracts, ethers.js/web3.js integration, DApp architecture, security patterns, and AI-enhanced blockchain development (ChatWeb3, Aider + Gemini 2024).
pump-swarm
Coordinated multi-wallet trading on Pump.fun.
trading-solana
Trade tokens on Solana DEXes - Jupiter, Raydium, Orca, Meteora, Pump.fun.
public
For agents: This document explains how to integrate with Clodds APIs.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).