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.
npx agentmods add rules/sunra-ai/sunra-clients/generalgit 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/general)<a href="https://agentmods.dev/rules/sunra-ai/sunra-clients/general"><img src="https://agentmods.dev/badge/rules/sunra-ai/sunra-clients/general.svg" alt="Measured on agentmods" 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 | $0.01566 | $0.01566 |
| Opus 5 | $0.00783 | $0.00783 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
general 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules for sunra.ai Client Libraries
Project Overview
This is a monorepo containing client SDKs for sunra.ai, a platform for deploying and running AI models. The repository includes:
- Client Libraries: JavaScript/TypeScript, Python, and Java clients
- Server Proxy: Framework adapters for secure API calls
- Examples: Demo applications for various frameworks
- Packages: Shared configurations and utilities
Repository Structure
sunra-clients/
├── clients/ # Client SDKs
│ ├── javascript/ # TypeScript/JavaScript client
│ ├── python/ # Python client
│ └── java/ # Java/Kotlin client
├── server-proxy/ # Framework proxy adapters
├── examples/ # Demo applications
├── packages/ # Shared configurations
└── apps/ # Internal applications
Development Guidelines
1. Monorepo Management
- Use pnpm as the package manager (specified in
packageManager) - Follow Turbo build system patterns for task orchestration
- Use Changesets for versioning and publishing
- Maintain workspace dependencies with
workspace:*references
2. Code Quality Standards
- TypeScript: Use strict mode, prefer explicit types over
any - Python: Follow PEP 8, use type hints, maintain
py.typedfiles - Java: Follow Google Java Style Guide, use proper annotations
- Testing: Write comprehensive tests for all client functionality
- Linting: Use ESLint for JS/TS, flake8 for Python, Checkstyle for Java
3. Client Library Patterns
JavaScript/TypeScript Client
- Use axios for HTTP requests
- Implement EventSource for streaming
- Support both CommonJS and ESM exports
- Provide TypeScript definitions
- Use vitest for testing
Python Client
- Use httpx for HTTP requests with async support
- Implement Server-Sent Events for streaming
- Support both sync and async APIs
- Use pytest with pytest-asyncio for testing
- Maintain py.typed for type checking
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.
- yesterday First seen · 201 lines · 1,566 tokens per session scan A 393ecfd87773
general is a cursor rule published in the GitHub repository sunra-ai/sunra-clients (7 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,566 tokens to every session, about $0.0078 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 2026-09-04.
Other cursor rules, from other repositories
drizzle-patterns
Drizzle ORM patterns and database conventions.
python--typescript-guide-cursorrules-prompt-file
Cursor rules for Python development with TypeScript guide integration.
django-python
Rules for writing Python services at PostHog (Python servers powered by the Django framework).
react-typescript
Rules for writing frontend code at PostHog (mostly React + Typescript with Kea).
rust
Rules for writing Rust services at PostHog. Focuses on writing async Rust with Tokio and encoding general Rust best practices from the Rust book and docs.
typescript
For Typescript.