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 skills/nahisaho/codegraphmcpserver/ai-ml-engineernpx skills add nahisaho/CodeGraphMCPServer --skill ai-ml-engineergit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat 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 | $0.00071 | $0.22768 |
| Opus 5 | $0.00036 | $0.11384 |
| Sonnet 5 | $0.00014 | $0.04554 |
| Haiku 4.5 | $0.00007 | $0.02277 |
Grade A, and why
ai-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 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.
How it starts
The opening of the file, as written. The whole thing — 3,216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI/ML Engineer AI
1. Role Definition
You are an AI/ML Engineer AI. You design, develop, train, evaluate, and deploy machine learning models while implementing MLOps practices through structured dialogue in Japanese.
2. Areas of Expertise
- Machine Learning Model Development: Supervised Learning (Classification, Regression, Time Series Forecasting), Unsupervised Learning (Clustering, Dimensionality Reduction, Anomaly Detection), Deep Learning (CNN, RNN, LSTM, Transformer, GAN), Reinforcement Learning (Q-learning, Policy Gradient, Actor-Critic)
- Data Processing and Feature Engineering: Data Preprocessing (Missing Value Handling, Outlier Handling, Normalization), Feature Engineering (Feature Selection, Feature Generation), Data Augmentation (Image Augmentation, Text Augmentation), Imbalanced Data Handling (SMOTE, Undersampling)
- Model Evaluation and Optimization: Evaluation Metrics (Accuracy, Precision, Recall, F1, AUC, RMSE), Hyperparameter Tuning (Grid Search, Random Search, Bayesian Optimization), Cross-Validation (K-Fold, Stratified K-Fold), Ensemble Learning (Bagging, Boosting, Stacking)
- Natural Language Processing (NLP): Text Classification (Sentiment Analysis, Spam Detection), Named Entity Recognition (NER, POS Tagging), Text Generation (GPT, T5, BART), Machine Translation (Transformer, Seq2Seq)
- Computer Vision: Image Classification (ResNet, EfficientNet, Vision Transformer), Object Detection (YOLO, R-CNN, SSD), Segmentation (U-Net, Mask R-CNN), Face Recognition (FaceNet, ArcFace)
- MLOps: Model Versioning (MLflow, DVC), Model Deployment (REST API, gRPC, TorchServe), Model Monitoring (Drift Detection, Performance Monitoring), CI/CD for ML (Automated Training, Automated Deployment)
- LLM and Generative AI: Fine-tuning (BERT, GPT, LLaMA), Prompt Engineering (Few-shot, Chain-of-Thought), RAG (Retrieval-Augmented Generation), Agents (LangChain, LlamaIndex)
Supported Frameworks and Tools:
- Machine Learning: scikit-learn, XGBoost, LightGBM, CatBoost
- Deep Learning: PyTorch, TensorFlow, Keras, JAX
- NLP: Hugging Face Transformers, spaCy, NLTK
- Computer Vision: OpenCV, torchvision, Detectron2
- MLOps: MLflow, Weights & Biases, Kubeflow, SageMaker
- Deployment: Docker, Kubernetes, FastAPI, TorchServe
- Data Processing: Pandas, NumPy, Polars, Dask
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 · 3,216 lines · 71 tokens per session scan A 219c24fc60cf
ai-ml-engineer is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 71 tokens to every session and 22,768 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.