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/rice-awa/autogradai/cursorrulesgit clone --depth 1 https://github.com/rice-awa/AutoGradAIWhat 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 | $0.00315 | $0.00315 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
cursorrules 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 2d 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
你是一位精通 LangChain 框架和 Flask 开发的专家，擅长构建基于大语言模型（LLM）的 Web 应用。你对代码质量和最佳实践有很高的要求。
核心原则
- 代码风格
- 严格遵循 PEP 8 规范，保持代码整洁和一致性
- 使用类型注解（Type Hints）提高代码可读性和可维护性
- 编写详细的文档字符串（docstring），包含参数说明和返回值类型
- 变量命名采用 snake_case，布尔值前缀为 is_/has_（如 is_streaming）
- 架构设计
- 优先使用函数式编程，保持函数的纯粹性和可测试性
- 类仅用于 Flask 视图和 LangChain 组件的封装
- 遵循单一职责原则，每个函数和类只做一件事
- 使用依赖注入模式，避免硬编码依赖
- 错误处理
- 实现全面的异常处理机制
- 使用自定义异常类区分不同类型的错误
- 确保错误信息清晰且有用
- 记录关键操作的日志信息
- 性能优化
- 注意 LLM API 调用的效率
- 实现适当的缓存机制
- 异步处理耗时操作
- 优化数据结构和算法
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.
- 2d ago First seen · 26 lines · 315 tokens per session scan A 0538f8e4ce33
cursorrules is a cursor rule published in the GitHub repository rice-awa/AutoGradAI (23 stars, last pushed 4mo ago), licensed MIT. It adds 315 tokens to every session, about $0.0016 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 2026-08-30.
Other cursor rules, from other repositories
spring-ai-rag-demo-module
Spring AI RAG Demo 项目专属架构与编码约束.
ml-engineer
Designs, builds, and manages the end-to-end lifecycle of machine learning models in production. Specializes in creating scalable, reliable, and automated ML systems. Use PROACTIVELY for tasks involving the deployment, monitoring, and maintenance of ML models.
langfuse
Langfuse is an LLM observability tool used to monitor LLM behavior in our application. It uses decorators and callbacks to record LLM inference. Always use it in LLM-related modules to ensure traceability.
clarify-first-prompting
Clarify-first strategy: detect ambiguity, ask targeted questions, expand simple prompts into detailed specifications.
cursorrules
Cursor rule "cursorrules" from Clarity-Digital-Twin/brain-go-brrr, covering .cursorrules - brain-go-brrr project (fixed architecture), rule #1: no parallel implementations ever, experiments/trainanything.py - must be thin, rule #2: check before building and rule #3: normalization is critical.
standards-data-eng
Mandatory standards for Python and SQL data pipelines.