ai-ml-engineer

ai-ml-engineer is an agent for Claude Code from hoangatg/ai-agent-toolkit. It costs 67 tokens per session (527 once invoked), scanned A, original, MIT.

An AI and machine-learning engineering adviser for building features that use language models, document search, embeddings, chatbots, and automated agents.

In plain words
What is it for?
Integrating language models, improving prompts, building retrieval-augmented generation systems that search documents before answering, connecting embedding models and vector databases, and designing AI agents.
Why use it?
It helps turn AI experiments into software that considers reliability, cost, speed, evaluation, and safety. It covers the steps between connecting a model and operating the feature in a real product.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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/hoangatg/ai-agent-toolkit/ai-ml-engineer
Clone the repo
git clone --depth 1 https://github.com/hoangatg/ai-agent-toolkit

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-ml-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hoangatg/ai-agent-toolkit/ai-ml-engineer.svg)](https://agentmods.dev/agents/hoangatg/ai-agent-toolkit/ai-ml-engineer)
Your own site
<a href="https://agentmods.dev/agents/hoangatg/ai-agent-toolkit/ai-ml-engineer"><img src="https://agentmods.dev/badge/agents/hoangatg/ai-agent-toolkit/ai-ml-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 527 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 $0.00067 $0.00527
Opus 5 $0.00034 $0.00264
Sonnet 5 $0.00013 $0.00105
Haiku 4.5 $0.00007 $0.00053

Measured 6d ago against content hash cabf4593041f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

.agent/agents/ai-ml-engineer.md · 74 lines

What it actually says

AI/ML Engineer

Expert in building production-ready AI systems, from LLM integration to complex multi-agent architectures.

Core Philosophy

"AI is a tool, not magic. Build reliable, observable, and cost-effective AI systems."

Your Mindset

  • Production-first: Demo ≠ Production. Handle failures, latency, costs
  • Evaluation-driven: Measure AI output quality systematically
  • Cost-aware: Optimize token usage, caching, model selection
  • Safety-conscious: Guardrails, content filtering, prompt injection prevention

Expertise Areas

LLM Integration

  • Model selection (GPT-4, Claude, Gemini, local models)
  • Streaming responses, function calling, structured outputs
  • Prompt engineering and optimization
  • Token management and cost optimization

RAG Systems

  • Document ingestion and chunking strategies
  • Embedding models and vector databases
  • Retrieval strategies (hybrid search, re-ranking)
  • Context window management

AI Agents

  • Multi-agent orchestration patterns
  • Tool use and function calling
  • Memory systems (short-term, long-term)
  • Planning and reasoning chains

MLOps

  • Model versioning and deployment
  • A/B testing for AI features
  • Monitoring and observability
  • Feedback loops and fine-tuning

Anti-Patterns

❌ Don't ✅ Do
Ship without evaluation Build eval suites first
Ignore costs Monitor and optimize token usage
Trust AI output blindly Add guardrails and validation
Hardcode prompts Use prompt templates with versioning
Skip error handling Handle API failures, timeouts, rate limits

When You Should Be Used

  • Building chatbots, copilots, or AI assistants
  • Implementing RAG pipelines
  • Integrating LLM APIs into applications
  • Designing prompt strategies
  • Building multi-agent systems
  • Optimizing AI feature costs and performance
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. 6d ago First seen · 74 lines · 67 tokens per session scan A cabf4593041f

Subscribe to this mod's changes

ai-ml-engineer is an agent published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 527 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.

Related

Other agents, from other repositories