A service for buying verified external data for AI agents one byte at a time with USDC, a cryptocurrency dollar equivalent. It checks the data against a cryptographic record before the agent acts on it.

Use it for signed checks such as payment-address risk, sanctions screening, package safety, market positioning, and liquidation events.

It helps agents avoid acting on altered or untrusted data when the source and integrity of the information matter.

payperbyte — Skill for Claude Code and Codex by 0rkz/byte-mcp-server

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 0rkz/byte-mcp-server --skill byte-mcp-server

Clone the repo

git clone --depth 1 https://github.com/0rkz/byte-mcp-server

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/0rkz/byte-mcp-server/byte-mcp-server/github.svg)](https://agentmods.dev/skills/0rkz/byte-mcp-server/byte-mcp-server)

Your own site

<a href="https://agentmods.dev/skills/0rkz/byte-mcp-server/byte-mcp-server"><img src="https://agentmods.dev/badge/skills/0rkz/byte-mcp-server/byte-mcp-server/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/0rkz/byte-mcp-server/byte-mcp-server"><img src="https://agentmods.dev/badge/skills/0rkz/byte-mcp-server/byte-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,961 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	$0.00191	$0.01961
Opus 5.5	$0.00076	$0.00784
Sonnet 5.5	$0.00038	$0.00392
Haiku 4.5	$0.00019	$0.00196

Measured 1mo ago against content hash f66e17e191d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

payperbyte 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/assert-deps.mjs, scripts/buy-oracle.mjs, scripts/check-version-claims.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PayPerByte (BYTE Library) — verified per-byte data for agents

PayPerByte is a data layer for AI agents. An agent discovers a first-party feed, pays per byte in USDC over x402 (a wallet signs an EIP-3009 transferWithAuthorization — no API key, no signup, no token), receives the payload, and then verifies it against an on-chain EIP-712 PayloadAttestation before acting on it. That verify step is the wedge: the agent does not assume the data is intact, it proves it.

When to use this skill

Reach for PayPerByte when the task needs external data the agent will act on and provenance matters — i.e. you want to be able to prove the data was not altered. Good triggers:

"Should I pay this address?" — the Address Reputation Oracle returns a signed ALLOW/WARN/BLOCK verdict for (domain, receiving address, amount, chain) before an agent releases USDC (price in the 402 challenge).
"Screen <address / name> against sanctions lists" (sanctions-screen), "is <npm/PyPI package> safe to install / deprecated" (pkg-verdict).
"Current exchange positioning snapshot" (positioning-snapshot), "recent liquidation events" (liquidation-stream).
"What's the weather / are there recent earthquakes" (weather, earthquakes).
"Threat-intel / IOCs / exploit signals" (threat-intel), "is <runtime/version> end-of-life" (runtime-eol).
"Fact-check this claim with cited sources" (evidence-pack).

Do not use it for: general reasoning, or data the model already knows reliably. Note that paid x402 calls spend real USDC — see Status.

Status (state this honestly)

x402 pay-per-call rail (byte_buy_data): Base mainnet, eip155:8453, real USDC (Circle USDC, EIP-3009, 6 decimals). Per-feed price is quoted in the 402 challenge and listed at https://x402.payperbyte.io/feeds. Every paid 200 returns an X-BYTE-Attestation EIP-712 receipt over the exact response bytes.
On-chain layer (subscriptions, broadcasts, fact-oracle escrow): Arbitrum Sepolia testnet, chain 421614 / eip155:421614, settled in a testnet MockUSDC. Mainnet for this layer is gated on an external security audit.
The EIP-712 PayloadAttestation signing domain (literal name BYTE Library) is anchored on eip155:421614 regardless of which rail the agent paid on; an off-chain attestation is not a claim that the verdict was broadcast on-chain.
No token. No external-user, revenue, or traction claims.
PRIVATE_KEY signs real Base-mainnet USDC for buys AND testnet txs for the on-chain tools. Use a dedicated wallet holding only what you intend to spend.

Read the full file on GitHub · 148 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · +5 lines · +7 tokens per session f66e17e191d7
2mo ago Changed · -3 tokens per session 6ee109fa92a7
2mo ago First seen · 143 lines · 187 tokens per session scan A aade797011cf

Subscribe to this mod's changes

payperbyte is a skill published in the GitHub repository 0rkz/byte-mcp-server (1 stars, last pushed 5d ago), licensed MIT. It adds 191 tokens to every session and 1,961 once invoked, about $0.0008 per session on Opus 5.5. 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.

Web3 and blockchain agent-commerce ai-agents arbitrum data-marketplace depin mcp

payperbyte next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
payperbyte0rkz/byte-mcp-server	Skill	1	5d ago	MIT	A	191	Claude Code, Codex
agent-commercedevlab-group/agent-commerce	Skill	62	yesterday	Apache-2.0	B	85	Claude Code
x402aomi-labs/skills	Skill	8	2d ago	MIT	A	84	Claude Code
sui-publishmission69b/t2000	Skill	23	1mo ago	MIT	A	133	Claude Code
t2000-jobmission69b/t2000	Skill	23	1mo ago	MIT	A	164	Claude Code
sui-object-modelmission69b/t2000	Skill	23	1mo ago	MIT	A	152	Claude Code
t2000-setupmission69b/t2000	Skill	23	1mo ago	MIT	A	113	Claude Code