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/sunra-ai/sunra-clientsWrote 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/sunra-ai/sunra-clients/qa)<a href="https://agentmods.dev/rules/sunra-ai/sunra-clients/qa"><img src="https://agentmods.dev/badge/rules/sunra-ai/sunra-clients/qa/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/sunra-ai/sunra-clients/qa"><img src="https://agentmods.dev/badge/rules/sunra-ai/sunra-clients/qa.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 | $0.02092 | $0.02092 |
| Opus 5.5 | $0.00837 | $0.00837 |
| Sonnet 5.5 | $0.00418 | $0.00418 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
qa scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **API Testing**: Postman, curl, HTTPie How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sunra Clients - Senior QA Engineer Role Document
Overview
This document defines the role and responsibilities of a Senior QA Engineer for the Sunra Clients project, a multi-language SDK suite that provides client libraries for Java/Kotlin, JavaScript/TypeScript, and Python, along with comprehensive examples and server proxy utilities.
Project Structure Analysis
The project consists of:
- Core SDKs: Java (sync/async/kotlin), JavaScript/TypeScript, Python
- Examples: Demo applications in multiple languages and frameworks
- Server Proxy: Utilities for various server frameworks
- Documentation: README files, code examples, and configuration guides
QA Responsibilities
1. SDK Testing & Validation
1.1 Java SDK Testing
Components to Test:
client/- Main synchronous clientclient-async/- Asynchronous client implementationclient-kotlin/- Kotlin-specific client
Test Areas:
- API Compatibility: Verify all public APIs work as documented
- Error Handling: Test exception handling in
SunraExceptionandSunraValidationException - Authentication: Validate
CredentialsResolverandCredentialsInterceptor - Queue Operations: Test all queue client operations (submit, status, cancel, subscribe)
- HTTP Layer: Verify
HttpClientand proxy interceptor functionality - Configuration: Test
ClientConfigandApiOptions - Async Operations: Ensure async client properly handles concurrent operations
- Kotlin Interoperability: Test Kotlin-specific features and syntax
Critical Test Cases:
// Test authentication failure scenarios
// Test network timeout handling
// Test malformed response handling
// Test concurrent queue operations
// Test resource cleanup and connection pooling
1.2 JavaScript/TypeScript SDK Testing
Components to Test:
- Core client functionality in
client.ts - Queue operations in
queue.ts - Request handling in
request.ts - Storage mechanisms in
storage.ts - Configuration management in
config.ts
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 · 271 lines · 2,092 tokens per session scan A eaf9d5dc9079
qa is a cursor rule published in the GitHub repository sunra-ai/sunra-clients (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,092 tokens to every session, about $0.0084 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other cursor rules, from other repositories
bun-test
When mocking entire modules, use mock.module(path, callback) (1) .
playwright
Playwright e2e guidelines distilled from PR.
omni-rewriter
Omni-Rewriter prompt-expansion framework conventions.
fuzzing
Fuzzing setup and guidelines for skia-rs.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.