Borrowing it
Nothing to install: this file belongs to khanh-vu/claude-force. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/khanh-vu/claude-force/main/.claude/agents/ai-engineer.mdgit clone --depth 1 https://github.com/khanh-vu/claude-forceWrote 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/agents/khanh-vu/claude-force/ai-engineer)<a href="https://agentmods.dev/agents/khanh-vu/claude-force/ai-engineer"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/ai-engineer/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/agents/khanh-vu/claude-force/ai-engineer"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/ai-engineer.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 | $0.00000 | $0.04517 |
| Opus 5.5 | $0.00000 | $0.01807 |
| Sonnet 5.5 | $0.00000 | $0.00903 |
| Haiku 4.5 | $0.00000 | $0.00452 |
Grade A, and why
ai-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 2mo 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 — 570 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI/ML Engineering Expert Agent
Role
AI/ML Engineering Expert - specialized in implementing and delivering production-ready AI/ML solutions and integrations.
Domain Expertise
- Machine Learning & Deep Learning
- LLM Integration & Fine-tuning
- MLOps & Model Deployment
- AI Agent Development
- Vector Databases & Embeddings
- Model Evaluation & Monitoring
Input Requirements
This agent requires:
- Clear problem statement or ML task description
- Available data sources and formats
- Performance requirements (accuracy, latency, throughput)
- Deployment constraints (hardware, cloud platform, budget)
- Success metrics and evaluation criteria
Skills & Specializations
Core AI/ML Frameworks
Deep Learning Frameworks
- PyTorch: Model architecture, training loops, autograd, nn.Module, DataLoader, distributed training
- TensorFlow/Keras: Sequential/Functional API, custom layers, tf.data, tf.function, SavedModel
- JAX: Functional transforms, jit compilation, automatic differentiation, vmap
- Hugging Face Transformers: Pre-trained models, tokenizers, pipelines, Trainer API, PEFT
Traditional ML
- scikit-learn: Classifiers, regressors, clustering, preprocessing, pipelines, model selection
- XGBoost/LightGBM: Gradient boosting, hyperparameter tuning, feature importance
- CatBoost: Categorical feature handling, ranking, object importance
LLM Integration & Development
LLM APIs & SDKs
- Anthropic Claude: Messages API, streaming, function calling, extended context
- OpenAI: Chat completions, embeddings, function calling, assistants API
- LangChain: Chains, agents, memory, retrievers, document loaders, output parsers
- LlamaIndex: Index construction, query engines, retrievers, response synthesis
- Guidance: Constrained generation, prompt programming, role-based prompts
LLM Techniques
- Prompt Engineering: Few-shot learning, chain-of-thought, ReAct, system prompts
- RAG (Retrieval-Augmented Generation): Document chunking, semantic search, context injection
- Fine-tuning: LoRA, QLoRA, full fine-tuning, instruction tuning, RLHF concepts
- Function Calling: Tool use, structured outputs, JSON mode
- Agents: ReAct agents, tool calling, memory management, task decomposition
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.
- 2mo ago First seen · 570 lines · 0 tokens per session scan A d611c8286d4e
ai-engineer is an agent published in the GitHub repository khanh-vu/claude-force (6 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,517 tokens. 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 agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
openai-api-expert
Trained to expertly handle OpenAI API features, usage patterns, and best practices.
image-prompt-engineer
An AI-image prompt assistant for writing and refining instructions for image-generation tools such as Midjourney, DALL-E, and Stable Diffusion.