ai-engineer

ai-engineer is an agent for Claude Code from khanh-vu/claude-force. It costs 0 tokens per session (4,517 once invoked), scanned A, original, MIT.

Um agente especializado em criar e colocar em produção soluções de inteligência artificial e aprendizagem automática, sistemas que aprendem padrões a partir de dados.

In plain words
What is it for?
Serve para desenvolver modelos, integrar modelos de linguagem, preparar dados, publicar sistemas e acompanhar o seu funcionamento.
Why use it?
Ajuda a transformar uma ideia de IA num sistema implementável, considerando dados, desempenho, custos, infraestrutura e avaliação.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/khanh-vu/claude-force/ai-engineer
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

Made for: Claude Code.

Wrote 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.

agentmods badge for ai-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/khanh-vu/claude-force/ai-engineer.svg)](https://agentmods.dev/agents/khanh-vu/claude-force/ai-engineer)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,517 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04517
Opus 5 $0.00000 $0.02259
Sonnet 5 $0.00000 $0.00903
Haiku 4.5 $0.00000 $0.00452

Measured 5d ago against content hash d611c8286d4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 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.

.claude/agents/ai-engineer.md · 570 lines

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

Read the full file on GitHub · 570 lines

Changes

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.

  1. 5d ago First seen · 570 lines · 0 tokens per session scan A d611c8286d4e

Subscribe to this mod's changes

ai-engineer is an agent published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo 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.

Related

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.

github/awesome-copilot · 24 tokens

Research Harness Engineer

Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.

github/awesome-copilot · 56 tokens

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

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".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens