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/dcloudio/uni-ai-xWrote 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/dcloudio/uni-ai-x/api)<a href="https://agentmods.dev/rules/dcloudio/uni-ai-x/api"><img src="https://agentmods.dev/badge/rules/dcloudio/uni-ai-x/api/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/dcloudio/uni-ai-x/api"><img src="https://agentmods.dev/badge/rules/dcloudio/uni-ai-x/api.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 | $0.00300 | $0.00300 |
| Opus 5.5 | $0.00120 | $0.00120 |
| Sonnet 5.5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
api 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
Global API (no uni. prefix required)
Get system information: getApp(), getSystemInfoSync() Lifecycle management: application-level events such as onLaunch and onShow
Platform native APIs
Android/iOS/Harmony/Web Mini Program can be directly called by the native interface of all platforms (import through import) Example: import Build from 'android.os.Build' to get the device model
Cross-platform encapsulation API
Network request: uni.request (Promise supported) File operation: uni.writeFile (overwrite/append mode needs to be explicitly declared) Location service: uni.getLocation (need to dynamically apply for location permission)
Cloud Service API
uniCloud database: uniCloud.database() File storage: uniCloud.uploadFile (supports multipart upload)
UI Component API
Custom component communication: $emit/$refs binding UI drawing: uni.createCanvasContext (WebGL supported)
Key usage specifications
- iOS does not support direct calls to Swift APIs in JS-driven mode, and must be encapsulated as uts plug-ins
- Dynamic permission application process: Registered permission listener: uni.addInterceptor('beforeEnter') Permission verification: uni.checkSetting({scope: 'scope.userLocation'}) Pop-up application: uni.authorize({scope: 'scope.camera'})
- The native API must be encapsulated as a uni_modules plugin
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 · 34 lines · 300 tokens per session scan A cf84bd4508bf
api is a cursor rule published in the GitHub repository dcloudio/uni-ai-x (86 stars, last pushed 2d ago), licensed Apache-2.0. It adds 300 tokens to every session, about $0.0012 per session on Opus 5.5. 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 2026-09-01.
Other cursor rules, from other repositories
api-creation-guide
Cursor rule "api-creation-guide" from HeeGyeong/ComposeSample, covering api creation guide rules, requirements, api call function, constraints and expected results.
api-ui-binding
Cursor rule "api-ui-binding" from HeeGyeong/ComposeSample, covering api and ui binding creation rules, requirements, 1. dto creation, 2. api interface and 3. api call function implementation.
contentstack-ios-cda
Contentstack CDA patterns – Stack/Config, HTTP, retry, callbacks, Content Delivery API.
mobile-api-generation-flow
Explain backend-to-mobile API generation flow.
dependency-injection
Hilt dependency injection rules: modules, scoping, testing, Compose integration.
android-networking-retrofit-okhttp
Build Android networking stacks with Retrofit, OkHttp, interceptors, API contracts, and resilient error handling.