What is xfuel-route-compute?

A preview and status checker for XFuel's compute router, which chooses among available providers such as Theta EdgeCloud, RapidAPI, local MCP, Akash, Render, and AWS Bedrock.

Checking provider availability, filtering by chain or model, inspecting server health, previewing routing, and confirming the provider that actually handled a task.

It helps determine which provider may run a task and whether the required server, chain, or model is available before submitting work.

xfuel-route-compute — Skill for Claude Code and Codex by XFuel-Lab

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-route-compute

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-route-compute/github.svg)](https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-route-compute)

Your own site

<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-route-compute"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-route-compute/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-route-compute"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-route-compute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 837 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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.00837
Opus 5	$0.00046	$0.00418
Sonnet 5	$0.00019	$0.00167
Haiku 4.5	$0.00009	$0.00084

Measured 10d ago against content hash b421f98beb3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

xfuel-route-compute 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-route-compute/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XFuel: Route / Inspect Compute

Preview routing and provider availability before (or instead of) submitting work.

Prerequisites

XFUEL_API_URL, XFUEL_API_KEY. See ../_shared/reference/env-and-endpoints.md.

Parameters

Name	Required	Description
`chain_id`	no	Filter intent chain: `theta` \| `akash` \| `bittensor` \| `osmosis`.
`model`	no	Model slug to check (informational).

The 6-tier priority router

Tasks route first-available, lowest-cost (see repo AGENTS.md / circuits/theta-inference):

Tier	Provider	Enabled by env (server-side)
1	Theta EdgeCloud	`THETA_EDGECLOUD_API_KEY`
2	RapidAPI inference	`THETA_RAPIDAPI_KEY`
3	MCP (local)	`THETA_MCP_ENDPOINT`
4	Akash Network	`AKASH_*`
5	Render Network	`RENDER_API_KEY`
6	AWS Bedrock (last resort)	`AWS_*`

Today the public /task-request path may not run the full waterfall — see docs/design/M2M_ROUTING_UNIFICATION.md. The routedTo / provider_tag fields in /task-status and the TaskSettled webhook are authoritative for what actually ran.

Procedure

Read server health to see configured fees, chains, and listener status:

import { XFuelClient } from 'xfuel-sdk';
const client = new XFuelClient({ baseUrl: process.env.XFUEL_API_URL, apiKey: process.env.XFUEL_API_KEY });
const health = await client.getHealth();
// health.chains, health.message_types, health.fee_config, health.ai_listener

To learn the actual provider for a task, submit via xfuel-submit-inference and read routedTo / provider_tag from the status/webhook.
Return a routing preview: enabled tiers (from health/listener status), the default chain, and the fee model (0.5% default).

Cost preview (payment rails)

To preview the price of a task per payment rail before submitting, call POST /task-quote (read-only): it returns the USDC-via-x402 amount (default rail, on Base) and the TFUEL amount. Provider routing (this skill) and payment rail (xfuel-submit-inference payment param) are independent — a task can run on any tier and settle in USDC or TFUEL. See ../_shared/reference/payments-x402.md.

Read the full file on GitHub · 82 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.

10d ago First seen · 82 lines · 93 tokens per session scan A b421f98beb3f

Subscribe to this mod's changes

xfuel-route-compute is a skill published in the GitHub repository XFuel-Lab/xfuel-protocol (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 93 tokens to every session and 837 once invoked, about $0.0005 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.

Cloud DevOps and cloud ai-agents mcp model-context-protocol theta x402 zk-proofs

agoragentic-deploy

Prepare a bounded Agoragentic deployment handoff or preview. Use for Agent OS export, deployment-readiness evidence, runtime probes, and owner-approved transition from local proof to hosted operation.

rhein1/agoragentic-integrations · 45 tokens

api-workers

Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.

cyanheads/obsidian-mcp-server · 51 tokens

coolify

Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys…

StuMason/coolify-mcp · 156 tokens

modal

Use when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code. Prefer local execution for normal repo work; use Modal sandboxes for isolation, hardware access, or one-shot heavy compute.

BlockRunAI/blockrun-mcp · 62 tokens

discovery-patterns

Configure ServiceNow Discovery — schedules, IP ranges, credential affinities, MID Server assignment, custom probes/sensors, identification rules, and run-status monitoring on discovery tables.

serac-labs/serac · 40 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens