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/obolnetwork/obol-stack/bridgingnpx skills add ObolNetwork/obol-stack --skill bridginggit clone --depth 1 https://github.com/ObolNetwork/obol-stackWhat 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 | $0.00128 | $0.04707 |
| Opus 5 | $0.00064 | $0.02354 |
| Sonnet 5 | $0.00026 | $0.00941 |
| Haiku 4.5 | $0.00013 | $0.00471 |
Grade A, and why
bridging 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: { "openclaw": { "emoji": "🌉", "requires": { "bins": ["cast", "python3", "curl"] } } } How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridging
Move value between Ethereum L1 and the L2s the Stack touches: Arbitrum One (42161), Robinhood Chain (4663, Arbitrum Nitro), and Base (8453, OP Stack). Bridging is the highest-stakes routine operation an agent can do — fake bridge contracts are a top drain vector, and canonical withdrawals lock capital for a week. This skill is about doing it safely and, just as often, about recognising when NOT to do it at all.
Signing goes through the agent's remote-signer (ethereum-local-wallet
skill); reads go through eRPC (ethereum-networks skill). All bridge
addresses come from the addresses skill references — every one was
verified on-chain (eth_getCode + eth_call) on 2026-07-10.
Iron rules — no exceptions:
- Verify every bridge contract address before sending. It must appear
in
addresses/references/bridges.mdoraddresses/references/robinhood-chain.md, AND return real bytecode on-chain right now (rpc.sh code <addr>—0xmeans EOA, abort; theinspectskill'scontract.py check <addr>gives a fuller verdict: proxy, verified source, labels). Fake bridge contracts are a top drain vector. Never use a bridge address from web search, a DM, a chat log, or your own memory. - Confirm with the user before bridging — state the amount, the exact route, the expected time BOTH directions (getting back matters), and the total cost including destination-side claim gas. Never bridge autonomously.
- First bridge on any new route = small test amount. Confirm arrival before sending the real amount.
- Never bridge the whole treasury. Keep gas plus working capital on the origin chain — you may need to act there while funds are in flight.
- Canonical withdrawals are a 7-DAY CAPITAL LOCKUP plus a separate L1 claim transaction (L1 gas). Treat withdrawn funds as illiquid until claimed. Any plan that assumes those funds are usable sooner is wrong.
- Bridged ERC-20 addresses DIFFER per chain. Resolve the destination
token via the gateway router's
calculateL2TokenAddress(l1Token)— never reuse the L1 address, never trust an explorer search result by token name (Robinhood Chain's explorer is full of scam "USDC"). - Ensure destination-chain ETH for gas BEFORE bridging ERC-20s — or bridge ETH first. Tokens you can't move are tokens you don't have.
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.
- 2d ago First seen · 329 lines · 128 tokens per session scan A d2bb398626c9
bridging is a skill published in the GitHub repository ObolNetwork/obol-stack (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 128 tokens to every session and 4,707 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
kurtosis-ethereum
Run Ethereum multi-client devnets using Kurtosis and the ethpandaops/ethereum-package. Use for spinning up local devnets, syncing public testnets, validating cross-client interop, testing fork transitions, shadowforks, running assertoor checks, debugging CL/EL client interactions, or verifying new feature…
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).
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
public
For agents: This document explains how to integrate with Clodds APIs.
copy-trading
Automatically copy trades from successful wallets on Polymarket and crypto.
acp
Enable agent-to-agent commerce with on-chain escrow, cryptographic agreements, and service discovery.