nexflow-smf-route-matrix-v1

nexflow-smf-route-matrix-v1 is a skill for Claude Code, Codex from NexFlow-SMF/nexflow-smf-public. It costs 46 tokens per session (706 once invoked), scanned A, original, MIT.

A skill for comparing paid routes for x402-style cryptocurrency payments, such as USDC on Base. It sends payment details to NexFlow SMF and returns available facilitators with pricing and other route information.

In plain words
What is it for?
Use it to select a facilitator, compare payment routes, or prepare a price quote for another user. x402 is a payment flow in which an HTTP service can require payment before responding.
Why use it?
It avoids choosing a payment facilitator without comparing fees, expected delay, and recent success rates.

Skill for Claude CodeCodex

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

Good fit Use it to select a facilitator, compare payment routes, or prepare a price quote for another user. x402 is a payment flow in which an HTTP service can require payment before responding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nexflow-smf/nexflow-smf-public/smf-route-matrix
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 NexFlow-SMF/nexflow-smf-public --skill smf-route-matrix
Clone the repo
git clone --depth 1 https://github.com/NexFlow-SMF/nexflow-smf-public

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 nexflow-smf-route-matrix-v1

README.md
[![agentmods](https://agentmods.dev/badge/skills/nexflow-smf/nexflow-smf-public/smf-route-matrix/github.svg)](https://agentmods.dev/skills/nexflow-smf/nexflow-smf-public/smf-route-matrix)
Your own site
<a href="https://agentmods.dev/skills/nexflow-smf/nexflow-smf-public/smf-route-matrix"><img src="https://agentmods.dev/badge/skills/nexflow-smf/nexflow-smf-public/smf-route-matrix/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 nexflow-smf-route-matrix-v1

Your own site · 80×15
<a href="https://agentmods.dev/skills/nexflow-smf/nexflow-smf-public/smf-route-matrix"><img src="https://agentmods.dev/badge/skills/nexflow-smf/nexflow-smf-public/smf-route-matrix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 706 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 $0.00046 $0.00706
Opus 5 $0.00023 $0.00353
Sonnet 5 $0.00009 $0.00141
Haiku 4.5 $0.00005 $0.00071

Measured 12d ago against content hash d79ccc9ed8c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nexflow-smf-route-matrix-v1 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 12d 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.

nexflow-smf-skills/smf-route-matrix/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use this skill

Use this skill whenever you need to:

  • Decide which facilitator to use for a payment.
  • Compare total fees, estimated latency, or recent success rate across routes.
  • Prepare price quotes for downstream users.

Do not use this skill for post-settlement auditing; use the settlement receipt skill instead.

How to call the HTTP API

  • Method: POST
  • URL: https://api.nexflow.xyz/api/smf/v1/route-matrix
  • Auth: x402 (expect HTTP 402 with PRICE headers if payment is required)

Request body

Send JSON:

{
  "asset": "USDC",
  "network": "eip155:8453",
  "amount": "10.0",
  "side": "send",
  "preferences": {
    "max_hops": 3,
    "prefer_latency_ms": 1500
  }
}

Fields:

  • asset (string, required): Token symbol, e.g. "USDC".
  • network (string, required): CAIP-2 network ID, e.g. "eip155:8453" for Base mainnet.
  • amount (string, required): Human-readable amount, e.g. "10.0".
  • side (string, optional): "send" or "receive". Default "send".

Response shape

On success (2xx) you receive JSON:

{
  "asset": "USDC",
  "network": "eip155:8453",
  "amount": "10.0",
  "routes": [
    {
      "facilitator": "base-main-smf",
      "total_fee": "0.04",
      "latency_ms": 850,
      "success_rate_30d": 0.992
    }
  ]
}

Interpretation: choose the route with the best trade-off between total_fee, latency_ms, and success_rate_30d for your use case.

Pricing and x402 behavior

NexFlow SMF uses x402 for pay-per-use billing.

Typical price range: 0.01–0.05 USDC on Base per call.

The exact price is advertised via the HTTP 402 response and PAYMENT-REQUIRED x402 header.

Always:

  1. Make an initial call.
  2. Read the 402 price.
  3. Decide whether to proceed with payment.

Test / sandbox mode

To avoid real settlement in tests:

  • Add header: X-Nexflow-Test: 1
  • Use small amounts (e.g. "1.0") for smoke tests.

In test mode, the service returns simulated routes with deterministic values that are safe to log and discard.

Read the full file on GitHub · 96 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. 12d ago First seen · 96 lines · 46 tokens per session scan A d79ccc9ed8c3

Subscribe to this mod's changes

nexflow-smf-route-matrix-v1 is a skill published in the GitHub repository NexFlow-SMF/nexflow-smf-public (0 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 706 once invoked, about $0.0002 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.