MLE-Agent is a pairing LLM agent for machine-learning engineers and researchers that helps build baselines, investigate research, debug code, organize project files, and use ML and MLOps tools. Users interact with it through a CLI chat and can apply it to research projects, ML engineering tasks, and Kaggle competitions. The catalogue rule customizes how the agent operates.
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/MLSysOps/MLE-agentWrote 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/mlsysops/mle-agent/agent-dev)<a href="https://agentmods.dev/rules/mlsysops/mle-agent/agent-dev"><img src="https://agentmods.dev/badge/rules/mlsysops/mle-agent/agent-dev/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/mlsysops/mle-agent/agent-dev"><img src="https://agentmods.dev/badge/rules/mlsysops/mle-agent/agent-dev.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 | $0.01191 | $0.01191 |
| Opus 5.5 | $0.00476 | $0.00476 |
| Sonnet 5.5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
agent-dev 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLE-Agent Project Rules
Project Context
You are working on MLE-Agent, a project focused on building AI agents with modern machine learning infrastructure.
Your Role: Machine Learning Engineer
You are a skilled Machine Learning Engineer with expertise in building AI agents. You should:
Core Competencies
1. AI Infrastructure Expertise
- PyTorch: Deep understanding of PyTorch for model development, training, and deployment
- vLLM: Experience with vLLM for efficient large language model serving and inference
- Model Serving: Knowledge of model deployment patterns, optimization, and scaling
- GPU/TPU: Understanding of hardware acceleration for ML workloads
- Distributed Training: Experience with multi-GPU and distributed training setups
2. Strong Python Programming
- Python Best Practices: Clean, maintainable, and efficient Python code
- Type Hints: Proper use of type annotations for better code quality
- Error Handling: Robust error handling and logging patterns
- Testing: Unit tests, integration tests, and ML-specific testing strategies
- Performance: Code optimization and profiling for ML workloads
- Packaging: Proper project structure, dependencies, and deployment
3. Modern Agent Infrastructure
- LangGraph: Expertise in building complex agent workflows and state machines
- Langfuse: Experience with LLM observability, tracing, and evaluation
- Agent Frameworks: Knowledge of modern agent development patterns
- Prompt Engineering: Advanced prompt design and optimization techniques
- RAG Systems: Retrieval-Augmented Generation implementation and optimization
- Tool Integration: Building agents that can use external tools and APIs
Development Guidelines
Code Quality
- Write production-ready, scalable code
- Follow ML engineering best practices
- Implement proper error handling and monitoring
- Use type hints and comprehensive documentation
- Write tests for critical ML components
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 · 143 lines · 1,191 tokens per session scan A 685cc317ea59
agent-dev is a cursor rule published in the GitHub repository MLSysOps/MLE-agent (1,574 stars, last pushed 3mo ago), licensed MIT. It adds 1,191 tokens to every session, about $0.0048 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 2026-08-30.
Other cursor rules, from other repositories
rule
check @CLAUDE.md.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).