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 stellar/stellar-dev-skill --skill agentic-paymentsgit clone --depth 1 https://github.com/stellar/stellar-dev-skillWrote 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/stellar/stellar-dev-skill/agentic-payments)<a href="https://agentmods.dev/skills/stellar/stellar-dev-skill/agentic-payments"><img src="https://agentmods.dev/badge/skills/stellar/stellar-dev-skill/agentic-payments/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/stellar/stellar-dev-skill/agentic-payments"><img src="https://agentmods.dev/badge/skills/stellar/stellar-dev-skill/agentic-payments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.01804 |
| Opus 5.5 | $0.00052 | $0.00722 |
| Sonnet 5.5 | $0.00026 | $0.00361 |
| Haiku 4.5 | $0.00013 | $0.00180 |
Grade A, and why
agentic-payments 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 1mo 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 "https://friendbot.stellar.org?addr=RECIPIENT_G..." How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Payments: x402 + MPP
Two complementary protocols for AI-agent and machine-to-machine payments on Stellar. Pick based on who depends on whom and how often the agent pays.
Quick decision
| x402 | MPP Charge | MPP Session | |
|---|---|---|---|
| Per-request on-chain tx? | Yes (via facilitator) | Yes (SAC) | No (off-chain commits) |
| Needs facilitator? | Yes — hosted or your own (options) | No | No |
| Client needs XLM? | No (fees sponsored) | Optional (feePayer) |
Yes |
| Setup complexity | Low | Low | Medium (deploy contract first) |
| Best for | Quickest setup, fee-free clients | No third-party dep | High-frequency agents |
- Selling an API, want zero-XLM clients → x402 Seller in x402.md
- Calling an x402 API from an agent → x402 Buyer in x402.md
- Selling an API, no facilitator dependency → Charge mode in mpp.md
- Agent making many requests per session → Session mode in mpp.md
- Sold an API, now want agents to find it → Discovery in mpp.md
- Unsure → x402 (lowest friction to get started)
All protocols use USDC (SEP-41 SAC) by default; stellar:testnet / stellar:pubnet CAIP-2 network IDs.
Read the file that matches the task
This file carries the decision table, the shared testnet account setup, and the USDC address reference. The protocol playbooks live alongside it:
| Task | File |
|---|---|
| Sell a paid API via a facilitator (zero-XLM clients), build an x402 buyer agent | x402.md |
| Facilitator-free per-request payments (Charge) or channel-backed sessions (Session) | mpp.md |
| Publish an OpenAPI discovery document so agents find your paid API | Discovery |
| Create/fund testnet accounts, add USDC trustlines, get testnet USDC | Testnet setup (below) |
| Which USDC address goes where (classic issuer vs SAC) | Two USDC addresses (below) |
What ships with it
2 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.
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 · +6 tokens per session 56ee9da71ea0
- 1mo ago First seen · 119 lines · 125 tokens per session scan A 2af48a37773b
agentic-payments is a skill published in the GitHub repository stellar/stellar-dev-skill (54 stars, last pushed 3d ago), licensed Apache-2.0. It adds 131 tokens to every session and 1,804 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
marginfi
MarginFi — Solana lending and borrowing.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…