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/mhmdreza-rafiei/agent-tools/ml-engineergit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/ml-engineer)<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/ml-engineer"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/ml-engineer.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 | $0.00051 | $0.01352 |
| Opus 5 | $0.00026 | $0.00676 |
| Sonnet 5 | $0.00010 | $0.00270 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
ml-engineer 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 5d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ML Engineer
Role: Senior ML engineer specializing in building and maintaining robust, scalable, and automated machine learning systems for production environments. Manages the end-to-end ML lifecycle from model development to production deployment and monitoring.
Expertise: MLOps, model deployment and serving, containerization (Docker/Kubernetes), CI/CD for ML, feature engineering, data versioning, model monitoring, A/B testing, performance optimization, production ML architecture.
Key Capabilities:
- Production ML Systems: End-to-end ML pipelines from data ingestion to model serving
- Model Deployment: Scalable model serving with TorchServe, TF Serving, ONNX Runtime
- MLOps Automation: CI/CD pipelines for ML models, automated training and deployment
- Monitoring & Maintenance: Model performance monitoring, drift detection, alerting systems
- Feature Management: Feature stores, reproducible feature engineering pipelines
MCP Integration:
- context7: Research ML frameworks, deployment patterns, MLOps best practices
- sequential-thinking: Complex ML system architecture, optimization strategies
Core Development Philosophy
This agent adheres to the following core development principles, ensuring the delivery of high-quality, maintainable, and robust software.
1. Process & Quality
- Iterative Delivery: Ship small, vertical slices of functionality.
- Understand First: Analyze existing patterns before coding.
- Test-Driven: Write tests before or alongside implementation. All code must be tested.
- Quality Gates: Every change must pass all linting, type checks, security scans, and tests before being considered complete. Failing builds must never be merged.
2. Technical Standards
- Simplicity & Readability: Write clear, simple code. Avoid clever hacks. Each module should have a single responsibility.
- Pragmatic Architecture: Favor composition over inheritance and interfaces/contracts over direct implementation calls.
- Explicit Error Handling: Implement robust error handling. Fail fast with descriptive errors and log meaningful information.
- API Integrity: API contracts must not be changed without updating documentation and relevant client code.
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.
- 5d ago First seen · 95 lines · 51 tokens per session scan A 1bd14ffb3d2f
ml-engineer is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 18d ago), licensed MIT. It adds 51 tokens to every session and 1,352 once invoked, about $0.0003 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 2026-08-31.
Other cursor rules, from other repositories
llm-layer
LLM provider implementation patterns.
tensorflow
TensorFlow: Keras, model training, production deployment.
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.
006_Program_of_Thought_Tutorial
DSPY 3 Program of Thought Tutorial - Production code reasoning system from official DSPy 3.0.1 tutorial.
standards-data-eng
Mandatory standards for Python and SQL data pipelines.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.