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 Parad0x-Labs/openclaw-skills --skill x402-gategit clone --depth 1 https://github.com/Parad0x-Labs/openclaw-skillsWrote 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/parad0x-labs/openclaw-skills/x402-gate)<a href="https://agentmods.dev/skills/parad0x-labs/openclaw-skills/x402-gate"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/x402-gate/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/parad0x-labs/openclaw-skills/x402-gate"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/x402-gate.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 | $0.00054 | $0.00708 |
| Opus 5.5 | $0.00022 | $0.00283 |
| Sonnet 5.5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
openclaw-x402-gate 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 2mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x402 Gate
Charge other agents for your OpenClaw skill or API. Mint a 402 challenge, verify the payment, then serve — funds settle straight to your own Solana wallet.
No custody. Your wallet address is config; the skill signs nothing and holds no keys.
When to use
- You want to monetize a skill, tool, or API by charging per-call in USDC.
- You want payments to land directly in your wallet with no intermediary custody.
When NOT to use
- You're serving something valuable but left
requireOnChainoff — structural checks alone don't prove settlement. Turn it on for revenue-grade gating. - You expected the skill to hold a balance for you. It doesn't, by design.
Tools
x402_challenge({ resource, description? })→ a 402 challenge body to send an unpaid caller. The price is seller config (priceUsdc), never a caller input.x402_verify({ header, resource })→ validates the payment; withrequireOnChain: true, confirms the transaction settled on Solana first.x402_rep_challenge()→ the reputation bar a caller must prove (see below).x402_rep_verify({ proof, publicSignals, expectedAgentCommitment? })→ verifies a private reputation proof against your policy.
Gate on private reputation (zk-rep)
Instead of (or alongside) charging per call, gate on proven track record: admit a
caller who proves it holds >= repMinCount settled receipts totalling >= repMinVolume
within repWindowSeconds, in an anchored receipt tree — learning no individual amount,
counterparty, or wallet. Set the bar in config (repMinCount, repMinVolume,
repWindowSeconds, repTrustedRoots); the caller answers with a Groth16 proof from
x402-pay's prove_reputation.
Verification is fail-closed on every seam: the proof must cryptographically verify, clear
your policy floor, build on a trusted anchored root, carry a single-use nullifier,
and (when you pass expectedAgentCommitment) match the caller's bound identity. Runs
off-chain today; a multi-party ceremony and on-chain trustless verification are next.
What ships with it
22 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.
- LICENSE 1.0 KB
- openclaw.plugin.json 5.4 KB
- package-lock.json 204 KB
- package.json 2.1 KB
- README.md 11 KB
- src/auth.ts 5.5 KB runs code
- src/constants.ts 3.0 KB runs code
- src/gate.ts 5.6 KB runs code
- src/index.ts 28 KB runs code
- src/onchain.ts 9.1 KB runs code
- src/rep.ts 11 KB runs code
- src/replay.ts 8.2 KB runs code
- src/track_record_vk.json 3.8 KB
- src/types.ts 2.6 KB runs code
- src/types/openclaw-host.d.ts 2.3 KB runs code
- src/types/snarkjs.d.ts 493 B runs code
- test/fee-split.test.mts 16 KB
- test/hooks.mjs 946 B runs code
- test/manifest.test.mjs 1.5 KB runs code
- test/register.mjs 165 B runs code
- test/rep.test.mts 7.7 KB
- tsconfig.json 424 B
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.
- 2mo ago First seen · 68 lines · 54 tokens per session scan A b37145ad07e7
openclaw-x402-gate is a skill published in the GitHub repository Parad0x-Labs/openclaw-skills (23 stars, last pushed 17d ago), licensed MIT. It adds 54 tokens to every session and 708 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
crypto-trading
Use ccxt (Python) for crypto prices, balances, and order actions across 100+ exchanges.
agent-arbitrage-tool
6 open tasks paying 1-3 ROSE ($3-9 each). Zero claimed. Workers keep 95%.
agent-micropayments-via-x402-protocol
Enable AI agents to make micropayments via x402 protocol. Use when purchasing browser sessions on Browserbase, scraping with Firecrawl, or any x402-compatible API. Handles wallet creation, funding, and automatic payment flows.
agent-evm-wallet-signing
Use this skill to safely create a wallet the agent can use for transfers, swaps, and any EVM chain transaction. Also supports raw signing.
agent-marketplace
Interact with the AgentMarket prediction market protocol on Base Sepolia. Create markets, trade YES/NO positions, provide liquidity, and resolve outcomes — all settled in USDC.
agents-bank
Version: 1.0.6 Publisher: AgentsBank Contact: [email protected] Status: 🟢 Public Release - Production Ready.