Borrowing it
Nothing to install: this file belongs to agenticpay-dev/agenticpay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agenticpay-dev/agenticpay/main/.claude/skills/agenticpay/SKILL.mdgit clone --depth 1 https://github.com/agenticpay-dev/agenticpayWrote 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/agenticpay-dev/agenticpay/agenticpay)<a href="https://agentmods.dev/skills/agenticpay-dev/agenticpay/agenticpay"><img src="https://agentmods.dev/badge/skills/agenticpay-dev/agenticpay/agenticpay/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/agenticpay-dev/agenticpay/agenticpay"><img src="https://agentmods.dev/badge/skills/agenticpay-dev/agenticpay/agenticpay.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 | $0.00100 | $0.01631 |
| Opus 5.5 | $0.00040 | $0.00652 |
| Sonnet 5.5 | $0.00020 | $0.00326 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
agentpay scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -i -X POST http://localhost:4021/tools/reverse \ How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentpay — pay-per-tool-call micropayments for AI agents
You are helping the user build, integrate, or troubleshoot agentpay, an open-source x402 payments stack for the MCP ecosystem on Solana.
Repo: https://github.com/krystiangw/agentpay (MIT)
Hosted devnet facilitator: https://agentpay-facilitator-e9b20a5fee6a.herokuapp.com
Landing page: https://krystiangw.github.io/agentpay/
Mental model
Three roles in every flow:
- Payer — an AI agent or its harness. Holds USDC, signs payment payloads.
- Resource server (
mcp-server) — exposes paid tools behind an HTTP 402 paywall. Each tool declares a price (e.g.$0.001 USDC). - Facilitator — verifies signed payment payloads, submits the USDC transfer on-chain via Solana, pays the SOL fee on the payer's behalf.
The packages in the monorepo:
| Package | Role |
|---|---|
@agenticpay/sdk |
USDC + wallet primitives, network config |
@agenticpay/cli |
agentpay CLI: wallet, balance, send |
@agenticpay/mcp-server |
Express server with x402 paywall middleware |
@agenticpay/facilitator |
Self-hostable x402 facilitator (verify + settle) |
Critical invariants (the day-1 footgun)
Network, asset, and RPC must be consistent. Mixing devnet network
(solana:EtWTRABZaYq6iMfeYKouRu166VU2xqa1) with mainnet USDC mint
(EPjFW...), or pointing the client at mainnet RPC while the facilitator
runs on devnet, produces transaction_simulation_failed: BlockhashNotFound.
Always verify all three line up.
| Network ID (CAIP-2) | USDC mint | RPC |
|---|---|---|
solana:EtWTRABZaYq6iMfeYKouRu166VU2xqa1 (devnet) |
4zMMC9srt5Ri5X14GAgXhaHii3GnPAEERYPJgZJDncDU |
https://api.devnet.solana.com |
solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp (mainnet) |
EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v |
https://api.mainnet-beta.solana.com |
For free experiments use devnet. The hosted facilitator at
agentpay-facilitator-e9b20a5fee6a.herokuapp.com supports both.
Common tasks
"Help me monetize an MCP server"
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.
- 2mo ago First seen · 144 lines · 100 tokens per session scan A 5bc3731e80fa
agentpay is a skill published in the GitHub repository agenticpay-dev/agenticpay (3 stars, last pushed 5d ago), licensed MIT. It adds 100 tokens to every session and 1,631 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
agentpay compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentpayagenticpay-dev/agenticpay | Skill | 3 | 5d ago | MIT | A | 100 | Claude Code |
| z-zero-paymentsDempty-glitch/Z-Zero-mcp | Skill | 1 | 14d ago | MIT | A | 55 | Claude Code |
| httpayerHTTPayer/mcp | Skill | 2 | 6mo ago | none | A | 138 | Claude Code |
| telnyx-x402-paymentteam-telnyx/ai | Skill | 224 | yesterday | MIT | A | 40 | Claude Code |
| nansen-dca-trackermoonpay/skills | Skill | 112 | 17d ago | MIT | A | 28 | Claude Code |
| x402tenequm/skills | Skill | 39 | yesterday | MIT | A | 63 | Claude Code, Codex |
| pnp-markets-solanainternet-court/internet-court-skill | Skill | 7.1k | 11d ago | none | A | 89 | Claude Code |