xfuel-verify-proof

xfuel-verify-proof is a skill for Claude Code, Codex from XFuel-Lab/xfuel-protocol. It costs 81 tokens per session (1,348 once invoked), scanned A, original, Apache-2.0.

A procedure for checking whether an XFuel task produced a valid SP1 settlement proof and, optionally, settled on Base. The proof confirms settlement data and an output commitment, but does not prove that a model's answer is correct.

In plain words
What is it for?
Use it after submitting an XFuel task to retrieve its proof, check the result hash and nullifier, optionally verify the on-chain settlement, and poll first if the task is not finished.
Why use it?
It helps distinguish a completed, replay-protected settlement from an unfinished or unverifiable task. It can also compare the recorded result with an expected output.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after submitting an XFuel task to retrieve its proof, check the result hash and nullifier, optionally verify the on-chain settlement, and poll first if the task is not finished.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xfuel-lab/xfuel-protocol/xfuel-verify-proof
Install

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.

Any agent
npx skills add XFuel-Lab/xfuel-protocol --skill xfuel-verify-proof
Clone the repo
git clone --depth 1 https://github.com/XFuel-Lab/xfuel-protocol

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for xfuel-verify-proof

README.md
[![agentmods](https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-verify-proof/github.svg)](https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-verify-proof)
Your own site
<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-verify-proof"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-verify-proof/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.

agentmods 80×15 button for xfuel-verify-proof

Your own site · 80×15
<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-verify-proof"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-verify-proof.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,348 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01348
Opus 5 $0.00041 $0.00674
Sonnet 5 $0.00016 $0.00270
Haiku 4.5 $0.00008 $0.00135

Measured 10d ago against content hash c268781bc490, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xfuel-verify-proof 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 10d 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.

packages/agent-skills/xfuel-verify-proof/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XFuel: Verify Proof

Confirm that an XFuel task produced a valid SP1 settlement proof and settled on-chain. (Tier-2 attests settlement metadata + output commitment — not black-box model correctness.)

Prerequisites

  • XFUEL_API_URL, XFUEL_API_KEY.
  • Optional on-chain check: Base RPC + ZK_VERIFIER_ADDRESS (ZKVerifierSP1 on Base). See ../_shared/reference/env-and-endpoints.md and docs/RUNTIME_STATE.md.

Parameters

Name Required Description
task_id yes Task id from xfuel-submit-inference.
expected_output no If provided, the skill recomputes the output hash and compares.
on_chain no If true, read ZKVerifierSP1 to confirm the nullifier was spent. Default false.

Procedure

  1. Fetch the proof:

    import { XFuelClient } from 'xfuel-sdk';
    const client = new XFuelClient({ baseUrl: process.env.XFUEL_API_URL, apiKey: process.env.XFUEL_API_KEY });
    const proof = await client.getProof(task_id);
    // proof.sp1_proof = { proof, publicInputs/publicValues, nullifier, provingTimeMs }
    

    If it returns 409 task_not_settled, the task is not complete yet — poll client.getTaskStatus(task_id) first.

  2. Inspect the public values (AITaskPublicValues): taskType, sourceChain, destChain, taskIdHash, senderHash, netAmount, feeAmount, feeBps, outputHash, blockHeight, timestamp, nonce. See ../_shared/reference/public-values.md.

  3. If expected_output was given, compute keccak256(expected_output) and assert it equals outputHash.

  4. If on_chain, read the verifier (read-only, no key needed) via the SDK on-chain module (uses the verified usedNullifiers accessor):

    import { XFuelOnChain } from 'xfuel-sdk/onchain'; // requires `ethers` peer dep
    const chain = new XFuelOnChain({
      rpcUrl: process.env.THETA_RPC_URL,            // Theta ETH-RPC (public or dedicated; not ZAN)
      zkVerifierAddress: process.env.ZK_VERIFIER_ADDRESS,
    });
    const spent = await chain.isNullifierUsed(proof.sp1_proof.nullifier);
    

Read the full file on GitHub · 122 lines

Changes

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.

  1. 10d ago First seen · 122 lines · 81 tokens per session scan A c268781bc490

Subscribe to this mod's changes

xfuel-verify-proof is a skill published in the GitHub repository XFuel-Lab/xfuel-protocol (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,348 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

x402-payments

Quote and settle OpenMesha x402 paywalled services (USDC on Base). Use when metering tool calls, outcome fees, or agent-to-agent settlement.

ANAMIZED/OpenMesha · 39 tokens

okx-cex-earn

A tool for managing several earning products on OKX, including savings, lending, staking, DeFi, Dual Investment, and AutoEarn. These products can use deposited cryptocurrency to generate returns, with terms that vary by product.

okx/agent-trade-kit · 274 tokens

blockrun

Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to make a…

BlockRunAI/blockrun-mcp · 241 tokens

surf

Surf (asksurf.ai) is RETIRED on BlockRun and the blockrunsurf tool was REMOVED in 0.49.0 — the gateway has answered every /v1/surf/ path with HTTP 410 endpointretired since 2026-09-06. Use this skill to route a former Surf question (on-chain SQL, wallet labels and net worth, CEX order books, social mindshare, news) to…

BlockRunAI/blockrun-mcp · 110 tokens

agoragentic-buzz-signed-workspace-evidence

Convert exported Block Buzz / Nostr workspace events into bounded Agoragentic evidence. Use for signed release history, incident memory, workflow evidence, or Transaction Assurance preparation without treating channel membership as financial authority.

rhein1/agoragentic-integrations · 54 tokens

agoragentic-anydoc-document-evidence

Convert a local Word, PowerPoint, spreadsheet, OpenDocument, RTF, EPUB, CSV, or text-based PDF into bounded Markdown and an Agoragentic evidence handoff. Use when an agent needs document contents plus runtime-verified provenance, explicit evidence coverage, known-loss warnings, and a pending-or-incomplete parse…

rhein1/agoragentic-integrations · 82 tokens