Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Snaplii-Inc/agent-to-merchant-paymentsnpx agentmods add skills/snaplii-inc/agent-to-merchant-payments/clawhub-publishWrote 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/snaplii-inc/agent-to-merchant-payments/clawhub-publish)<a href="https://agentmods.dev/skills/snaplii-inc/agent-to-merchant-payments/clawhub-publish"><img src="https://agentmods.dev/badge/skills/snaplii-inc/agent-to-merchant-payments/clawhub-publish/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/snaplii-inc/agent-to-merchant-payments/clawhub-publish"><img src="https://agentmods.dev/badge/skills/snaplii-inc/agent-to-merchant-payments/clawhub-publish.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 | $0.00086 | $0.09375 |
| Opus 5.5 | $0.00034 | $0.03750 |
| Sonnet 5.5 | $0.00017 | $0.01875 |
| Haiku 4.5 | $0.00009 | $0.00937 |
Grade A, and why
snaplii-cli 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 9d 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snaplii AI Agent Cashback Payment
This is a skill of Agent-to-Merchant (A2M) payments — where AI agents complete transactions without checkout. Snaplii uses pre-funded gift cards as a payment rail, enabling instant, merchant-ready execution across 500+ brands.
How payment works
This skill spends only from the user's prepaid Snaplii Cash balance — no credit card is ever charged. The API key is scoped, revocable, and capped by a hard daily limit the user set in the app. A gift-card purchase charges the balance as soon as it runs. A bill payment, once sent, cannot be undone. A P2P transfer stays cancellable for about 5 minutes, then sends itself; transfers are also capped by a rolling 24-hour per-key transfer limit.
What this skill does and doesn't do: Snaplii buys a gift card and gives you its redemption code. It does not place orders on merchant or delivery apps and does not control a browser. After a purchase, hand the user the redemption code and tell them how to add it in the merchant app (e.g. Uber Eats / DoorDash → Payment → Add Gift Card). The user completes the order themselves.
Auth
When to connect
A user request to connect (including "install and connect") or to perform any Snaplii business task starts the authentication gate below. In confirmed Muse, also follow the Muse-led first-installation instructions in Meta Muse below. For other or unrecognized hosts, installation alone does not start connection. Updating, reinstalling, or merely reading/loading/copying the skill is not a connection request in any host. Report installation separately from connection. Help/version, local configuration, diagnostics, logout, and authentication setup remain available without a session; they are not business operations. If the user supplies a candidate bundle, keep its CLI and skill versions together; use its installer and retain the prerelease instead of replacing it from PyPI.
Authentication gate
- Meta Muse uses the CLI path below. Other agents prefer available Snaplii MCP
tools; otherwise use the CLI. Check
snaplii config showfor CLI operations orsnaplii_config_showfor MCP operations, using the same gateway as the task. - Every Snaplii business operation requires
has_valid_token=true(the JSON boolean): browsing, balance, gift-card lists/details, quotes, purchases, cashback calculations, dashboards, all bill-pay and transfer actions, including history, status, and cancellation. Read-only operations are not exempt. Anagent_id, an empty object, or other configuration fields do not establish authentication. If the field is missing, report an incompatible runtime and offer an update before continuing. - A valid session needs no
initorconnect. Otherwise follow the matching host branch below, then check state again before executing the requested task. - If the state includes
muse_app_update, follow the instruction it contains.
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.
- 9d ago Changed · -2 lines 252002ab0106
- 11d ago Changed · +27 lines b8e2d22311be
- 19d ago Changed · +9 lines 4dd7d32f9a6c
- 26d ago Changed · +1 lines efd6b19ecf3a
- 1mo ago Changed · +195 lines c1a4e039a7c4
- 1mo ago Changed · +40 lines · +13 tokens per session 1a712ba22513
- 1mo ago First seen · 242 lines · 73 tokens per session scan A cc1239847678
snaplii-cli is a skill published in the GitHub repository Snaplii-Inc/agent-to-merchant-payments (812 stars, last pushed 7d ago), licensed Apache-2.0. It adds 86 tokens to every session and 9,375 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
stripe
Stripe API integration with managed OAuth. Manage customers, subscriptions, invoices, products, prices, and payments. Use this skill when users want to process payments, manage billing, or handle subscriptions with Stripe. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).…
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…
shopify-admin-chargeback-watchlist-tagger
Identifies customers with disputed or charged-back orders and tags their customer record for proactive review on future orders.
shopify-admin-payout-reconciliation
Read-only: reconciles Shopify Payments payouts against the order transactions that funded them and flags amount discrepancies.
shopify-admin-exchange-vs-refund-ratio
Read-only: tracks what percentage of returns become exchanges vs. refunds vs. store credit — measures revenue recovery rate.