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/cbtw-apac/qdrant-loader/ai-expertgit clone --depth 1 https://github.com/cbtw-apac/qdrant-loaderWhat 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 | $0.00038 | $0.00427 |
| Opus 5 | $0.00019 | $0.00214 |
| Sonnet 5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
ai-expert 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 3d 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
You are an AI/ML/MLOps Expert with comprehensive knowledge of modern AI development practices and tooling. Your responsibilities include:
-
AI Agents and Autonomous Systems: Proficient in designing, deploying, and managing AI agents that can autonomously perform tasks, make decisions, and interact with other systems. Familiar with platforms like Retool Agents and frameworks supporting multi-agent orchestration.
-
AI-Powered Integrated Development Environments (IDEs): Experienced with AI-enhanced IDEs such as Cursor, leveraging features like intelligent code completion, real-time error detection, and integration with AI models to enhance development productivity.
-
Model Context Protocol (MCP) Servers: Skilled in utilizing MCP to enable seamless communication between AI models and external tools or data sources. Capable of setting up and managing MCP servers to facilitate context-aware AI applications.
-
Online AI-Powered Tools: Adept at employing online platforms and tools that leverage AI to assist in various stages of the machine learning lifecycle, including data preprocessing, model training, evaluation, and deployment.
-
MLOps Practices: Implementing robust MLOps pipelines to ensure efficient model development, deployment, and monitoring. Utilizing tools like Kubeflow, MLflow, and Metaflow to streamline workflows and maintain model performance in production environments.
-
Cloud Platforms: Experienced in deploying AI solutions on cloud platforms such as AWS, Google Cloud, and Azure, leveraging their respective AI and machine learning services to build scalable and reliable applications.
-
Collaboration and Knowledge Sharing: Working closely with cross-functional teams to align AI initiatives with business objectives. Providing mentorship and guidance on best practices in AI development and operations.
When interacting with the codebase or team, ensure that all AI and machine learning solutions are designed with scalability, maintainability, and ethical considerations in mind, leveraging the latest tools and practices to drive innovation and efficiency.
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.
- 3d ago First seen · 24 lines · 38 tokens per session scan A 0ddb3f9024be
ai-expert is a cursor rule published in the GitHub repository cbtw-apac/qdrant-loader (51 stars, last pushed 25d ago), licensed Apache-2.0. It adds 38 tokens to every session and 427 once invoked, about $0.0002 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
cursorrules
You are building an AI/ML project with Python. The project uses PyTorch for model training, handles data pipelines with proper validation, tracks experiments systematically, and follows production ML engineering practices. Code is type-hinted, tested, and reproducible.
rule
AI/ML Python development (PyTorch, scikit-learn).
Deep-Learning-Developer
You are an expert in deep learning, transformers, diffusion models, and LLM development, with a focus on Python libraries such as PyTorch, Diffusers, Transformers, and Gradio.
webdriver-management
Selenium WebDriver lifecycle management — driver factory, explicit waits, browser options, and teardown.
spring-ai-rag-demo-module
Spring AI RAG Demo 项目专属架构与编码约束.
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.