obol-stack

"Buy from any x402-gated endpoint. Start with `go <url>` — it probes, detects the offer type, and runs the right flow. Expert flows underneath: `pay` for one-shot HTTP services (single authorization, no sidecar), `pay-agent` for one-shot streaming agent calls, and `buy` for long-running paid inference (pre-authorized batch via PurchaseRequest, exposed as `paid/<remote-model>`). Supports USDC (EIP-3009) and OBOL (Permit2). Zero signer access at runtime — spending is capped by design and nothing moves on-chain until a voucher is spent."

CLI-first Obol Stack development and QA runbook. Use when working on obol-stack lifecycle, obol CLI surfaces, x402 seller/buyer tests, live Base Sepolia OBOL smoke, Anvil fork regressions, ERC-8004 registration, LiteLLM paid routing, release-smoke, cloudflared, Renovate image bumps, or remote QA worktrees.

Verified contract addresses for major Ethereum protocols across mainnet and L2s. Use this instead of guessing. SKILL.md is an index — load the appropriate references/*.md file for the addresses you need. Start with references/obol-payments.md for the Stack's own rails (USDC + OBOL + Permit2 + ERC-8004 on the supported chains). Other categories include stablecoins, staking + Obol/Splits, DEXs, lending and DeFi, L2-native protocols, infrastructure (Safe, AA, Chainlink, EigenLayer, ENS, OpenSea), bridges (CCIP, Across), and major token addresses. Always verify on-chain via eth_getCode + eth_call before sending value.

Spawn durable child Hermes agents from inside Obol Stack. Creates child namespaces, optional profile/env Secrets, Agent CRDs, and optional ServiceOffers for x402-paid child services. Use when the user says 'spawn an agent', 'create a sub-agent', 'child agent', or wants a separate long-lived service agent. For deciding WHAT agent to build, whether it's good enough to sell, and how to price it, load sub-agent-business first.

End-to-end guide for monetizing GPU resources or HTTP services through obol-stack. Covers pre-flight checks, model detection, pricing research, selling via x402, ERC-8004 registration, and verification. Use when the user says 'monetize my machine', 'sell my GPU', or 'expose a paid API' — i.e. selling raw inference or a plain HTTP service. For selling a specialised agent's replies (the higher-margin path), use sub-agent-business instead.

"Sell access to services via x402 payment gating. Create ServiceOffer CRDs that automatically health-check upstreams, create payment-gated routes, and optionally pull models and register on ERC-8004. Supports inference, HTTP, and fine-tuning service types. Use for ServiceOffer plumbing: listing offers, checking/waiting on reconciliation status, creating or deleting offers. For the guided end-to-end walkthrough use monetize-guide; for selling a child agent's turns use sub-agent-business + agent-factory."

Build and run a paid sub-agent business: design specialised child agents whose replies are worth more than a raw model call, evaluate them honestly, price them, sell turns via x402, and iterate (or kill) based on revenue. Use when the user says 'build an agent people will pay for', 'productise my agent', 'agent business', 'what should I sell', 'is my agent good enough to charge for', or when deciding WHAT to sell and at WHAT price before reaching for agent-factory or sell.

Swap tokens on the chains the Obol Stack supports — USDC, WETH/ETH, and OBOL on Base and Ethereum mainnet via Uniswap V3. Use when earnings need converting (USDC → ETH for gas, consolidating USDC/OBOL revenue, rebalancing the agent treasury) or the user says 'swap', 'convert', 'sell my USDC', 'get ETH for gas'. Quote first, bound slippage, confirm with the user before sending.

Execute Ethereum transactions NOW — send ETH, approve tokens, call contracts, sign messages. Uses the in-cluster remote-signer (agents never touch private keys). Use this skill whenever the user wants to DO something onchain, not just learn about wallets.

Query Ethereum networks through the local RPC gateway. Use when asked about blocks, balances, transactions, gas prices, token balances, or any eth_* JSON-RPC method. All queries are read-only and routed through the in-cluster eRPC load balancer.

"Discover AI agents registered on the ERC-8004 Identity Registry. Search for agents by querying on-chain registration events, look up agent details (URI, owner, wallet), and fetch agent metadata. Read-only queries routed through the in-cluster eRPC gateway."

Current Ethereum gas prices, transaction costs, and the real economics of building on Ethereum today. Use when estimating costs, choosing between mainnet and L2s, or when a user asks about Ethereum being expensive. Counters the

"Coordinate distributed autoresearch experiments across GPU workers discovered via ERC-8004 and paid via x402 micropayments."

Run autonomous LLM optimization experiments (autoresearch) and publish optimized models for paid inference via x402.

Run a GPU worker that accepts paid autoresearch experiments over HTTP and monetize it through obol sell http.

How to read historical onchain data at scale — events, logs, The Graph subgraphs, Ponder, and indexing patterns. Use when building a backend that needs past blockchain state (not live queries — use ethereum-networks for that). Covers why you cannot loop through blocks and what to use instead.

Educational reference on Ethereum wallet types — EOAs, smart contract wallets, multisig (Safe), account abstraction (ERC-4337). Use when explaining wallet concepts, choosing a wallet architecture, or designing key management. NOT for sending transactions — use ethereum-local-wallet for that.

Monitor the Kubernetes cluster running the Obol Stack. Use when asked about pod status, logs, services, events, deployments, or diagnosing issues. Read-only access to own namespace via ServiceAccount.

DeFi legos and protocol composability on Ethereum and L2s. Major protocols per chain — Aerodrome on Base, GMX/Pendle on Arbitrum, Velodrome on Optimism — plus mainnet primitives (Uniswap, Aave, Compound, Curve). How they work, how to build on them, and how to combine them. Use when building DeFi integrations, choosing protocols on a specific L2, designing yield strategies, or composing existing protocols into something new.

The essential mental models for building onchain — focused on what LLMs get wrong and what humans need explained. "Nothing is automatic" and "incentives are everything" are the core messages. Use when your human is new to onchain development, when they're designing a system, or when they ask "how does this actually work?" Also use when YOU are designing a system — the state machine + incentive framework catches design mistakes before they become dead code.

Monitor distributed validator clusters via the Obol API. Use when asked about DVT cluster health, validator performance, operator status, exit coordination, or anything related to Obol, Charon, or distributed validators. Read-only — cannot create clusters or submit exits.

Ethereum Layer 2 landscape — Arbitrum, Optimism, Base, zkSync, Scroll, Unichain, Celo, and more. How they work, how to deploy on them, how to bridge, when to use which. Includes per-chain DeFi ecosystems and critical corrections. Use when choosing an L2, deploying cross-chain, or when a user asks about Ethereum scaling.

Ethereum token and protocol standards — ERC-20, ERC-721, ERC-1155, ERC-4337, ERC-8004, and newer standards. When to use each, how they work, key interfaces. Use when building tokens, NFTs, or choosing the right standard for a project.

Why build on Ethereum specifically. The AI agent angle — ERC-8004, x402, composability, permissionless deployment. Use when a user asks "should I build on Ethereum?", "why blockchain?", or when an agent needs to recommend a chain for a project.

Launch and test the k3d or k3s backend lifecycle (init, up, kubectl, down, purge). Use when you want to run a full integration test of a stack backend.