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/PaddleHQ/paddle-agent-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/paddlehq/paddle-agent-skills/plugin)<a href="https://agentmods.dev/plugins/paddlehq/paddle-agent-skills/plugin"><img src="https://agentmods.dev/badge/plugins/paddlehq/paddle-agent-skills/plugin/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/paddlehq/paddle-agent-skills/plugin"><img src="https://agentmods.dev/badge/plugins/paddlehq/paddle-agent-skills/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
paddle 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "paddle",
"description": "Paddle Billing skills and MCP servers for Claude Code.",
"author": {
"name": "Paddle",
"email": "[email protected]",
"url": "https://www.paddle.com"
},
"homepage": "https://developer.paddle.com/get-started/ai/claude-code/",
"repository": "https://github.com/PaddleHQ/paddle-agent-skills",
"license": "Apache-2.0",
"keywords": ["paddle", "billing", "payments", "subscriptions", "saas"],
"userConfig": {
"sandbox_api_key": {
"type": "string",
"title": "Paddle sandbox API key",
"description": "Sandbox API key (starts with pdl_sdbx_). Authenticates the paddle-sandbox MCP server. The paddle-live MCP server authorizes with OAuth in your browser, so it needs no key here.",
"sensitive": true
}
}
}
What it installs
The manifest is a name and a version. 11 skills, 3 MCP servers travel with it, and installing the plugin installs all of them — 493 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill paddle-billing-history A 82 tokens
- Skill paddle-subscription-sync A 35 tokens
- Skill paddle-subscription-update A 48 tokens
- Skill paddle-usage-based-billing A 55 tokens
- Skill paddle-webhooks A 32 tokens
- Skill paddle-catalog-setup A 43 tokens
- Skill paddle-checkout-web A 35 tokens
- Skill paddle-pricing-pages A 34 tokens
- Skill paddle-sandbox-testing A 34 tokens
- Skill paddle-customer-portal A 49 tokens
- Skill paddle-subscription-cancel A 46 tokens
- MCP server paddle-sandbox A not measured
- MCP server paddle-docs A not measured
- MCP server paddle-live A not measured
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 · 23 lines scan A 35f018877a8a
paddle is a plugin published in the GitHub repository PaddleHQ/paddle-agent-skills (9 stars, last pushed 2d ago), licensed Apache-2.0. 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 2026-08-31.
Other plugins, from other repositories
polar-skills
Official Polar skills for billing, subscriptions, and local development.
stripe-skills
Official Stripe skills for payments, billing, Connect, Apps, and API upgrades.
paypal
PayPal development plugin for Claude — integrate payments, subscriptions, invoices, disputes, and more using PayPal's APIs and MCP server.
snaplii-a2m-payment
Agent-to-Merchant payments — AI agents complete gift card transactions without checkout across 500+ brands via Snaplii.
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.
scvd-general-store
Evidence observatory: x402/MPP inspection, signed receipt checks and settlement attestations.