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 NexFlow-SMF/nexflow-smf-public --skill smf-budget-plangit clone --depth 1 https://github.com/NexFlow-SMF/nexflow-smf-publicWrote 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/nexflow-smf/nexflow-smf-public/smf-budget-plan)<a href="https://agentmods.dev/skills/nexflow-smf/nexflow-smf-public/smf-budget-plan"><img src="https://agentmods.dev/badge/skills/nexflow-smf/nexflow-smf-public/smf-budget-plan/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/nexflow-smf/nexflow-smf-public/smf-budget-plan"><img src="https://agentmods.dev/badge/skills/nexflow-smf/nexflow-smf-public/smf-budget-plan.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 | $0.00043 | $0.00629 |
| Opus 5 | $0.00022 | $0.00315 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
nexflow-smf-budget-plan-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.
How it starts
The opening of the file, as written. The whole thing — 81 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 when:
- A user or system has a fixed budget (e.g. 10 USDC) and you need to estimate how many SMF calls that allows.
- You are setting rate limits or caps based on cost.
- You are building "budget remaining" or "calls remaining" UX.
Do not use for real-time pricing of a single call; use simulate-charge or the paid endpoints for that.
HTTP API
- Method: POST
- URL:
https://api.nexflow.xyz/api/smf/v1/budget-plan - Auth: none (planning only; no payment).
Request body
Send JSON:
{
"budget_amount": "10.0",
"asset": "USDC",
"network": "eip155:8453",
"operation_mix": {
"route-matrix": 0.5,
"route-quote": 0.5
}
}
Fields:
- budget_amount (string, required): Total budget in human-readable form, e.g. "10.0".
- asset (string, optional): Token symbol. Default "USDC".
- network (string, optional): CAIP-2 network ID. Default "eip155:8453".
- operation_mix (object, optional): Weights per operation type (sum to 1.0). Default: equal weight across common paid operations. Omit for a single generic estimate.
Response shape
On success (2xx):
{
"budget_amount": "10.0",
"asset": "USDC",
"network": "eip155:8453",
"estimated_calls": 250,
"avg_cost_per_call": "0.04",
"breakdown": {
"route-matrix": 125,
"route-quote": 125
},
"disclaimer": "Estimates based on current average fees; actual usage may vary."
}
Use estimated_calls and breakdown for display or caps. Treat as approximate; actual fees can vary per call.
Pricing
This endpoint is free. No x402 payment is required.
Test usage
- Add header:
X-Nexflow-Test: 1for test mode. - Expect deterministic estimates (e.g. fixed avg cost) for automated tests.
Usage examples for agents
- "With a 5 USDC budget, how many route-matrix calls can we make on Base?"
- "Plan a budget mix: 60% route-matrix, 40% route-quote for 20 USDC."
- "Show the user how many API calls their current budget allows before topping up."
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.
- 12d ago First seen · 81 lines · 43 tokens per session scan A ada25c429009
nexflow-smf-budget-plan-v1 is a skill published in the GitHub repository NexFlow-SMF/nexflow-smf-public (0 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 629 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.
Other skills, from other repositories
piprail
Pay x402 paywalled URLs from a budget-bound, self-custodial crypto wallet across 10+ chains.
pinion-chain-intel
On-chain intelligence, transactions and wallet tools on Base. 9 x402-paywalled skills at $0.01 USDC each.
pinion-send
Construct an unsigned ETH or USDC transfer transaction on Base. Client signs and broadcasts. Costs $0.01 USDC via x402.
pinion-trade
Get an unsigned swap transaction via 1inch aggregator on Base. Includes approval tx if needed. Costs $0.01 USDC via x402.
pinion-fund
Check wallet balances and get funding instructions for Base. ETH and USDC. Costs $0.01 USDC via x402.
pinion-price
Get current USD price for any token on Base via Birdeye (CoinGecko fallback). Costs $0.01 USDC via x402.