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/trueLoving/PixuliWrote 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/rules/trueloving/pixuli/storage-plugin)<a href="https://agentmods.dev/rules/trueloving/pixuli/storage-plugin"><img src="https://agentmods.dev/badge/rules/trueloving/pixuli/storage-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/rules/trueloving/pixuli/storage-plugin"><img src="https://agentmods.dev/badge/rules/trueloving/pixuli/storage-plugin.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 | $0.00000 | $0.00300 |
| Opus 5.5 | $0.00000 | $0.00120 |
| Sonnet 5.5 | $0.00000 | $0.00060 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
storage-plugin 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
Storage Plugin
契约（@pixuli/core/plugins）
StoragePluginManifest+StorageProviderFactory→registry.register(manifest, factory)registry.create(pluginId, ProviderContext)返回StorageProviderProviderContext：platform、platformAdapter
官方插件结构
packages/plugin-provider-{id}/src/
manifest.ts # id、capabilities、configSchema
register.ts # registerXxxProvider(registry)
*StorageProvider.ts # 实现 list/upload/delete/buildImageUrl
index.ts # 公开 API
应用侧
- Bootstrap：
app/src/storage/registry.ts - 配置后创建：
createConfiguredStorageProvider(pluginId, config)→provider.configure(config)
禁止
- Provider 包内引入 React /
app/src/ui（@/ui） - core 内写 GitHub/Gitee API 具体实现（应在 provider 包）
参考
docs/02-system-design/03-plugin-system.md- 单测：
packages/*/src/__tests__/register.test.ts、packages/core/src/plugins/__tests__/
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 · 39 lines · 0 tokens per session scan A 932d476ae483
storage-plugin is a cursor rule published in the GitHub repository trueLoving/Pixuli (64 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 300 tokens. 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 cursor rules, from other repositories
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
tray-api
Regras e documentação da API Tray. Aplica quando o desenvolvedor trabalhar com autenticação OAuth, produtos, pedidos, clientes, webhooks, frete, pagamentos ou qualquer outro recurso da plataforma Tray. Inclui convenções obrigatórias de autenticação, formato de payload, rate limit e índice completo de skills com…
headless-all
Composite skill for the headless track. Apply when designing or modifying a BFF (Backend-for-Frontend) layer, middleware, or API proxy for a headless VTEX storefront. Covers BFF middleware architecture, public vs private API classification, VtexIdclientAutCookie management, API key protection, and secure request…
marketplace-all
Composite skill for the marketplace track. Apply when building catalog or SKU synchronization logic for VTEX marketplace seller connectors. Covers the changenotification endpoint, SKU suggestion lifecycle, product data mapping, price and inventory sync, and fulfillment simulation. Use for implementing seller-side…
payment-payment-provider-framework
Apply when designing or implementing a Payment Connector in VTEX IO. Covers PPF implementation, TypeScript 3.9.7 builder-hub constraints and safe dependency resolutions, configuration.json schema validation, PaymentProviderService clients wiring, Secure Proxy scope (authorize-only), ExternalClient vs…
payment-payment-ppp-pos
Apply when implementing a VTEX Payment Provider Protocol connector for Point of Sale (POS) payments on VTEX Sales App. Covers Venda Direta Credito and Venda Direta Debito manifest methods, the two-phase Payment App challenge (terminal connector then wait-for-confirmation), null card data on Create Payment…