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.
git clone --depth 1 https://github.com/paid-tw/skillsWrote 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/plugins/paid-tw/skills/ecpay)<a href="https://agentmods.dev/plugins/paid-tw/skills/ecpay"><img src="https://agentmods.dev/badge/plugins/paid-tw/skills/ecpay/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/plugins/paid-tw/skills/ecpay"><img src="https://agentmods.dev/badge/plugins/paid-tw/skills/ecpay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ecpay 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.
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.
What it actually says
{
"name": "ecpay",
"version": "1.1.0",
"description": "綠界科技(ECPay)串接指南 - 全方位金流、電子發票",
"author": {
"name": "paid-tw",
"email": "[email protected]",
"url": "https://github.com/paid-tw"
},
"homepage": "https://github.com/paid-tw/skills#ecpay",
"repository": "https://github.com/paid-tw/skills",
"license": "MIT",
"keywords": ["taiwan", "payment", "ecpay", "綠界", "金流", "invoice", "電子發票"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 37 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 First seen · 15 lines scan A d959abc6a20e
ecpay is a plugin published in the GitHub repository paid-tw/skills (282 stars, last pushed 7mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
sumup
Skills for SumUp payment integrations across terminal and online checkout flows.
finance-social-readers
Read-only social media and research feeds — Twitter/X, Discord, LinkedIn, Telegram, Y Combinator, plus a generic opencli fallback covering 100+ finance/research sources.
paypal
PayPal development plugin for Claude — integrate payments, subscriptions, invoices, disputes, and more using PayPal's APIs and MCP server.
tododeia marketplace
Payment integration tooling for Claude Code, from tododeia. Local-first plugins that write production payment code and block the insecure patterns as they are written.
client-operations
Back-office account operations and servicing workflows. Covers the full account lifecycle from opening through maintenance, transfers, reconciliation, and corporate actions.
scvd-general-store
Evidence observatory: x402/MPP inspection, signed receipt checks and settlement attestations.