Borrowing it
Nothing to install: this file belongs to salazarsebas/Cougr. 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/salazarsebas/Cougr/main/.claude/skills/agentic-payments/SKILL.mdgit clone --depth 1 https://github.com/salazarsebas/CougrWrote 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/salazarsebas/cougr/agentic-payments)<a href="https://agentmods.dev/skills/salazarsebas/cougr/agentic-payments"><img src="https://agentmods.dev/badge/skills/salazarsebas/cougr/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/salazarsebas/cougr/agentic-payments"><img src="https://agentmods.dev/badge/skills/salazarsebas/cougr/agentic-payments.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 | $0.00120 | $0.07058 |
| Opus 5.5 | $0.00048 | $0.02823 |
| Sonnet 5.5 | $0.00024 | $0.01412 |
| Haiku 4.5 | $0.00012 | $0.00706 |
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 today.
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 — 626 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 Channel | |
|---|---|---|---|
| Per-request on-chain tx? | Yes (via facilitator) | Yes (Soroban SAC) | No (off-chain commits) |
| Needs facilitator? | Yes (OZ Channels) | 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 → see x402 Seller below
- Calling an x402 API from an agent → see x402 Buyer below
- Selling an API, no facilitator dependency → see MPP Charge below
- Agent making many requests per session → see MPP Channel below
- Unsure → x402 (lowest friction to get started)
All protocols use USDC (SEP-41 SAC) by default; stellar:testnet / stellar:pubnet CAIP-2 network IDs.
Related skills
- The Soroban SACs the protocols call →
../soroban/SKILL.md - USDC and other classic assets →
../assets/SKILL.md - Wallets and signing in the buyer client →
../dapp/SKILL.md - RPC simulation / submission patterns →
../data/SKILL.md - SEP-41 (token interface) and related standards →
../standards/SKILL.md
Part 1: x402 - Paid APIs + Agent Buyer Clients
When to use x402
x402 is the right choice when:
- You want the fastest path to a paid API - minimal code, no contract deployment
- You want clients (including AI agents) to pay with zero XLM - the OZ Channels facilitator sponsors all network fees
- You're building on top of an existing x402 ecosystem (Coinbase, other chains)
Trade-off: you depend on OZ Channels (or a self-hosted relayer) for verification and settlement. If you need zero third-party dependency, use MPP Charge (Part 2 below) instead.
How x402 works on Stellar
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.
- today First seen · 626 lines · 120 tokens per session scan A d1ac15fdcd95
agentic-payments is a skill published in the GitHub repository salazarsebas/Cougr (53 stars, last pushed 17d ago), licensed MIT. It adds 120 tokens to every session and 7,058 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 2026-11-07.
agentic-payments compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentic-paymentssalazarsebas/Cougr | Skill | 53 | 17d ago | MIT | A | 120 | Claude Code |
| stellar-forgerylsherdamz-rgb/stellar-forge | Skill | 17 | 5d ago | MIT | A | 82 | Claude Code |
| agentic-paymentsrylsherdamz-rgb/stellar-forge | Skill | 17 | 5d ago | MIT | A | 38 | Claude Code |
| nirium-agentic-paymentsnirium-protocol/nirium-sdk | Skill | 2 | 1mo ago | Apache-2.0 | A | 128 | Claude Code, Codex |
| x402-stellar-paymentsCodeStrux/x402-stellar-kit | Skill | 0 | 25d ago | Apache-2.0 | A | 38 | Claude Code, Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | today | MIT | A | 13 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | today | MIT | A | 11 | Claude Code, Codex |