APIPark is an open-source gateway and developer portal for managing AI services and REST APIs through a common interface. Teams use it to connect models, publish APIs, manage applications and keys, standardize requests, and monitor usage.
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/APIParkLab/APIParkWrote 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/apiparklab/apipark/windsurfrules)<a href="https://agentmods.dev/rules/apiparklab/apipark/windsurfrules"><img src="https://agentmods.dev/badge/rules/apiparklab/apipark/windsurfrules/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/apiparklab/apipark/windsurfrules"><img src="https://agentmods.dev/badge/rules/apiparklab/apipark/windsurfrules.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 | $0.00521 | $0.00521 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
windsurfrules 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 today.
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
Create detailed components with these requirements:
- Use 'use client' directive for client-side components
- Style with Tailwind CSS utility classes for responsive design
- Use React Router for navigation
- Use Ant Design for UI components
- Use iconify React for icons (from @iconify/react package). Do NOT use other UI libraries unless requested
- Use local photos from public folder where appropriate, only valid URLs you know exist
- Create root layout.tsx page that wraps necessary navigation items to all pages
- MUST implement the navigation elements items in their rightful place i.e. Left sidebar, Top header
- Accurately implement necessary grid layouts
- Follow proper import practices:
- Use @/ path aliases
- Keep component imports organized
- Update current packages/core/src/pages/Root.tsx with new comprehensive code
- Don't forget root route (page.tsx) handling
- You MUST complete the entire prompt before stopping
11. Table component should use
import PageList from "@common/components/aoplatform/PageList.tsx"
- PageList component MUST use addNewBtnTitle for add button, NOT toolBarRender. Example:
<PageList
id="global_team"
className="pl-btnbase"
ref={pageListRef}
columns = {[...columns]}
request = {()=>getTeamList()}
showPagination={false}
addNewBtnTitle={$t('添加团队')}
addNewBtnAccess = "system.organization.team.add"
searchPlaceholder={$t("输入名称、ID、负责人查找团队")}
onAddNewBtnClick={()=>{openModal('add')}}
onSearchWordChange={(e)=>{setSearchWord(e.target.value)}}
onRowClick={(row:TeamTableListItem)=>(navigate(
../inside/${row.id}/setting))} /> - use
const { fetchData } = useFetch()to fetch http data,such as
fetchData<BasicResponse<{ profile: UserInfoType }>>('account/profile', { method: 'GET' }).then((response) => {
const { code, data, msg } = response
if (code === STATUS_CODE.SUCCESS) {
setUserInfo(data.profile)
dispatch({ type: 'UPDATE_USERDATA', userData: data.profile })
} else {
message.error(msg || $t(RESPONSE_TIPS.error))
}
})
- can't not import new package!
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.
- today First seen · 46 lines · 521 tokens per session scan A ef901266a031
windsurfrules is a cursor rule published in the GitHub repository APIParkLab/APIPark (1,811 stars, last pushed yesterday), licensed Apache-2.0. It adds 521 tokens to every session, about $0.0026 per session on Opus 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 2026-09-09.
Other cursor rules, from other repositories
next-js
Cursor rule "next-js" from superglue-ai/superglue, covering rules, structure, ai sdk and adding npm packages/dependencies.
upgrade-tests
// ✅ CORRECT: Upgrade package pattern await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }).
react-query-tests
// ✅ CORRECT: Legacy React Query pattern const ctx = konn() .beforeEach(() => createAppRouter()) .afterEach((ctx) => ctx?.close?.()) .done().
tanstack-react-query-tests
// ✅ CORRECT: Use await using for automatic cleanup await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }).
react-vite-web
Cursor rule "react-vite-web" from WellApp-ai/Well, covering web rules (react + vite), routing, component structure, state management and api integration.
01-web
Next.js 15 App Router, React, UI patterns.