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/buy-x402npx skills add ObolNetwork/obol-stack --skill buy-x402git 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/buy-x402)<a href="https://agentmods.dev/skills/obolnetwork/obol-stack/buy-x402"><img src="https://agentmods.dev/badge/skills/obolnetwork/obol-stack/buy-x402.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 | $0.00132 | $0.08028 |
| Opus 5 | $0.00066 | $0.04014 |
| Sonnet 5 | $0.00026 | $0.01606 |
| Haiku 4.5 | $0.00013 | $0.00803 |
Grade A, and why
buy-x402 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 5d 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.
curl -X POST http://litellm.llm.svc.cluster.local:4000/v1/chat/completions \ How it starts
The opening of the file, as written. The whole thing — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buy x402
Purchase access to remote x402-gated services.
Not sure which command? Use go. It probes the URL, reads the 402 to detect what's being sold, and dispatches with the right path, method, streaming mode, and timeout:
# Agent or chat-inference offer — one paid round of work, streamed:
python3 ${OBOL_SKILLS_DIR:-/data/.openclaw/skills}/buy-x402/scripts/buy.py go <url> --message 'your task'
# Plain HTTP offer — one paid request:
python3 ${OBOL_SKILLS_DIR:-/data/.openclaw/skills}/buy-x402/scripts/buy.py go <url>
go never creates persistent state; for a pre-authorized inference pool it points you at buy. The expert flows underneath, picked by usage shape:
pay <url>— single-shot. Probe the URL, sign one payment authorization, attachX-PAYMENT, send the request, return the response. Stateless. Use fortype:httpservices and any one-off purchase. Max loss = price of one request. Settlement normally lands only after the request succeeds — but a facilitator can submit the settle tx on-chain and then fail the request. When that happens the failure report prints⚠️ SETTLEMENT MAY HAVE COMPLETED ON-CHAINwith the tx hash: verify withbalance --chain <X>before retrying (mechanism: docs/observability.md, "Verify settlement against the chain"). Applies topay-agenttoo.pay-agent <url>— single-shot paid streaming agent call. Same payment shape aspay(one auth, X-PAYMENT, max-loss = price), but POSTs to<url>/v1/chat/completionswithstream: trueand forwards every SSE event verbatim to stdout as it arrives. No--model: atype:agentoffer runs its own model (the requestmodelfield is ignored), so you only send a prompt. Use this fortype:agentServiceOffers when the calling agent wants to consume the response itself (memory, tool-call traces, partial results) instead of routing it through LiteLLM as a paid alias. Default HTTP read timeout is 1 hour — agent calls can legitimately run for many minutes; override with--timeout <seconds>.buy <name>— pre-authorize a budget. Sign N authorizations up front (the buyer pays nothing yet), declare them in aPurchaseRequestCR, let thex402-buyersidecar redeem them transparently as the agent calls the model through LiteLLM atpaid/<remote-model>. Use for long-running paid inference. Max loss = N × price (only as vouchers are spent); runtime path holds zero signer access.buy <name> --model <id> --set-default— same asbuyabove, then adoptpaid/<remote-model>as the agent's own primary model, in-pod, by itself: an atomichermes config set model.defaultthat Hermes re-reads per request (effective next chat turn, no restart, no host-sideobol model prefer/obol model sync). Refuses if the model isn't selectable in LiteLLM. Pair with--auto-refillso the primary model doesn't brick when the pre-authorized budget runs out.
Both flows auto-detect the token + transfer method from the seller's 402 response. Currently supported: USDC via EIP-3009 (Base Sepolia, Base Mainnet, Ethereum Mainnet) and OBOL via Permit2 (Ethereum Mainnet).
Multi-currency offers (pick what you pay with). A seller can advertise several payment options (e.g. 1 USDC on Base OR 10 OBOL on Ethereum) in the 402 accepts[] array. probe lists them all. For go, pay, pay-agent, and buy, choose one with --token <SYMBOL> (e.g. --token OBOL), --network <chain>, and/or --payment-option <N> (the 1-based index from probe). With a single option the choice is automatic. With several and no selector: a TTY prompts; non-interactive runs auto-select the first option the wallet can afford (announced loudly, with the full option list, before any signing). --token/--network also act as a guard — if the filter matches no advertised option, it aborts rather than paying the wrong asset.
Money amounts (--budget, --cost-cap). Both accept atomic units (1500000), token units (1.5), or token units with a symbol ('1.5 USDC', '$1.50'). Anything with a decimal point, symbol, or $ is treated as token units and scaled by the asset's decimals; the parsed interpretation is echoed before signing. A symbol that contradicts the asset being paid with aborts.
What ships with it
3 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.
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.
- 5d ago First seen · 553 lines · 132 tokens per session scan A 801fc6e94a8a
buy-x402 is a skill published in the GitHub repository ObolNetwork/obol-stack (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 132 tokens to every session and 8,028 once invoked, about $0.0007 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…
defi
Interact with DeFi protocols on MAINNET via the ChainGPT plugin. Aave V3 (supply/borrow/repay/withdraw + health-factor monitoring across 7 chains), Lido stETH staking, EigenLayer restaking. Yield discovery: Pendle yield-trading markets (PT/YT), Morpho Blue lending markets + MetaMorpho vaults. Custody-free — plugin…
scheduled-autonomy
Run trading/DeFi strategies on a schedule — DCA every morning, grid rebalances, recurring health checks — using saved plans + the execution journal (duesteps/markstep) + Claude Code scheduled agents, with the agent wallet executing inside hard policy caps. Triggers - run this daily, schedule a DCA, recurring buy, set…
trade
Execute live DEX trades on MAINNET via the ChainGPT plugin. EVM swaps via OpenOcean (default, no key, 10 mainnets), 1inch v6 (key-gated, better blue-chip routing), or CoW Protocol (MEV-protected intent-based for large trades). Solana swaps via Jupiter. Custody-free — the plugin builds unsigned tx / EIP-712 intent, the…
drift
Read live Drift Protocol mainnet data — Solana's largest non-custodial perps DEX. Use for market scanning, funding analysis, orderbook depth, and user position auditing. The Solana-native alternative to Hyperliquid: same custody-free model (on-chain collateral, user-held keys), different blockchain. Read-only in this…
tron
Tron (TVM) support via the ChainGPT plugin — at parity with the EVM + Solana surfaces. Read balances/resources/tx, research (DexScreener), risk (GoPlus), build UNSIGNED native TRX + TRC-20 transfers (custody-free), SunSwap quotes, JustLend lending, and autonomous agent-wallet signing behind a deterministic policy…