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 XFuel-Lab/xfuel-protocol --skill xfuel-submit-inferencegit clone --depth 1 https://github.com/XFuel-Lab/xfuel-protocolWrote 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/xfuel-lab/xfuel-protocol/xfuel-submit-inference)<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-submit-inference"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-submit-inference/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/xfuel-lab/xfuel-protocol/xfuel-submit-inference"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-submit-inference.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 | $0.00115 | $0.01894 |
| Opus 5 | $0.00057 | $0.00947 |
| Sonnet 5 | $0.00023 | $0.00379 |
| Haiku 4.5 | $0.00012 | $0.00189 |
Grade A, and why
xfuel-submit-inference 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 9d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XFuel: Submit Verifiable Inference
Run an AI inference/compute task through XFuel's router and receive a settled, proof-backed receipt. Prefer the SDK over raw HTTP. Money + proofs live on Base.
Prerequisites
XFUEL_API_URL(defaulthttps://api.xfuel.app; usehttp://localhost:3002to self-host) andXFUEL_API_KEY(defaults to the public demo keyxfuel-demo).xfuel-sdkinstalled (npm install xfuel-sdk). See../_shared/reference/env-and-endpoints.md.
Parameters
| Name | Required | Description |
|---|---|---|
model |
yes (inference) | Live catalog id, e.g. xfuel/auto or theta/glm_5_2 (list via GET /v1/models). Retired llama-* names are rejected, not remapped. Maps to SDK modelId. |
input |
recommended | Prompt/string. You compute input_hash = keccak256(input) (the SDK takes input_hash, not the raw input). |
sender |
yes | Caller address (settlement attribution). |
amount |
no | Gross fee in USDC 6 decimals (10000 = $0.01). Default 1000000 ($1.00). |
chain_id |
no | base (default) | theta | bittensor | akash | osmosis. base = settlement home; others are routing / optional-rail hints. |
proof_system |
no | sp1 (default settlement proof). zkgpt is a retired/dev scaffold — not the Tier-3 path. |
callback_url |
no | Webhook to receive the TaskSettled event instead of polling. |
payment |
no | Payment rail. Default USDC via x402 ({ rail: 'usdc', network: 'base' }). Optional legacy rails may exist if the server enables them. |
subnet_id |
yes if chain_id=bittensor |
Bittensor subnet UID. |
Payment rail (USDC via x402 is the default)
XFuel's default rail is USDC via x402 — agent-native payment on Base against a machine-parseable 402 challenge. The SDK never holds keys.
// Default — USDC via x402 (agent-side wallet signs; SDK never holds keys)
"payment": { "rail": "usdc", "asset": "USDC", "network": "base", "maxAmount": "50000" }
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.
- 9d ago First seen · 140 lines · 115 tokens per session scan A b990a5c1f64f
xfuel-submit-inference is a skill published in the GitHub repository XFuel-Lab/xfuel-protocol (1 stars, last pushed 9d ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,894 once invoked, about $0.0006 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.
Other skills, from other repositories
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…
x402-payments
Quote and settle OpenMesha x402 paywalled services (USDC on Base). Use when metering tool calls, outcome fees, or agent-to-agent settlement.
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.
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…
opik-instrument
Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for "instrument my code", "add opik tracing", "add observability"…
aba-precision-protocol
FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.