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/xsolla/xsolla-ai-kitWrote 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/xsolla/xsolla-ai-kit/gemini-extension)<a href="https://agentmods.dev/plugins/xsolla/xsolla-ai-kit/gemini-extension"><img src="https://agentmods.dev/badge/plugins/xsolla/xsolla-ai-kit/gemini-extension/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/xsolla/xsolla-ai-kit/gemini-extension"><img src="https://agentmods.dev/badge/plugins/xsolla/xsolla-ai-kit/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
xsolla-ai-kit 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 4d 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": "xsolla-ai-kit",
"version": "1.1.0",
"description": "Xsolla agent skills toolkit — guided workflows from zero to a live game shop: a headless shop you host (payments, catalog, login, webhooks) or, in preview, an unpublished Shop Builder site assembled from a plain-language game description.",
"contextFileName": "AGENTS.md",
"mcpServers": {
"xsolla-docs": {
"httpUrl": "https://xsolla.mcp.kapa.ai"
}
}
}
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.
- 4d ago Changed 6523babc62ea
- 1mo ago First seen · 12 lines scan A b466c0eddc5c
xsolla-ai-kit is a plugin published in the GitHub repository xsolla/xsolla-ai-kit (7 stars, last pushed yesterday), 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 2026-09-10.
Other plugins, from other repositories
pagokit
Picks the right payment provider for your project and writes the integration — checkout, authenticated webhook, database schema, customer portal and refund path — with deterministic validators that BLOCK insecure writes as they happen. Three local engines back it: hook validators that cannot be argued with, a…
opsagent-shopify
MSApps OpsAgents Shopify plugin — full Admin API + Storefront MCP tools (products CRUD, files, orders, customers, themes, metafields), go-to-market guidance, and @opsagents/shopify-sdk typed contracts.
saleor-commerce
Expert subagent and skills for Saleor commerce development — GraphQL-only API with Graphene-Django, App development with Next.js SDK, webhooks (async/sync with subscription payloads), Dashboard extensions with App Bridge and MacawUI, Next.js storefronts, channels, catalog with typed attributes, transaction payment…
medusa-commerce
Expert subagent and skills for Medusa v2 development — custom modules with DML data models, workflows with compensation, API routes, subscribers, admin dashboard extensions, Next.js storefronts, payment and fulfillment providers, and TypeScript/Node.js patterns.
maestro-skills
Maestro Skills Hub & Cordis Plugin -- Magento 2 (architecture, linting, performance, security), Govard dev-environment orchestration, and the superpowers process-skills library (forked from obra/superpowers).
wake-storefront
Wake Commerce development assistance for headless storefronts. Teaches product queries, checkout flow, cart, customer API, and GraphQL patterns.