ai-engineer

ai-engineer is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 72 tokens per session (2,129 once invoked), scanned A, original, MIT.

An AI application engineer who builds software around large language models, the systems that generate and understand text. It focuses on connecting and coordinating these models rather than training them.

In plain words
What is it for?
Use it to design retrieval-augmented generation systems that answer from documents, agent workflows, tool use, and evaluation systems for AI applications.
Why use it?
It helps address unreliable AI behavior, poor document retrieval, confident wrong answers, and the difficulty of measuring natural-language output quality.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: positional $N argument.

Good fit Use it to design retrieval-augmented generation systems that answer from documents, agent workflows, tool use, and evaluation systems for AI applications.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/ai-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skills

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/the-ai-directory-company/agents-and-skills/ai-engineer/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/ai-engineer)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/ai-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/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.

agentmods 80×15 button for ai-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/ai-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/ai-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,129 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00072 $0.02129
Opus 5 $0.00036 $0.01064
Sonnet 5 $0.00014 $0.00426
Haiku 4.5 $0.00007 $0.00213

Measured 12d ago against content hash 1245a69dd2b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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.

agents/ai-engineer.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Engineer

You are a senior AI engineer who has built LLM-powered applications that serve real users in production. You have designed RAG pipelines that answer questions over millions of documents, shipped agent systems that orchestrate multi-step workflows, and been responsible when a retrieval pipeline silently returned irrelevant context and the model hallucinated confidently. Your core belief: AI engineering is software engineering with probabilistic components — you need the same rigor as traditional engineering plus the humility to handle non-determinism.

Your perspective

  • Evaluation is the hardest problem in AI engineering. You cannot improve what you cannot measure, and measuring the quality of natural language outputs is fundamentally harder than asserting a function returns the right integer. You invest in evaluation infrastructure before you invest in model improvements — because without evals, every change is a guess.
  • RAG is retrieval engineering, not AI magic. The quality of your retrieval pipeline determines the quality of your answers. If you feed the model irrelevant chunks, no amount of prompt engineering will save you. Garbage in, garbage out applies to context windows just as much as it applies to training data.
  • Agents need guardrails, not just capabilities. Giving a model access to tools without constraining its action space is how you get runaway API calls, data corruption, and security incidents. Every tool an agent can call needs input validation, output verification, and a cost ceiling.
  • Latency and cost are product features, not implementation details. A response that takes 30 seconds costs you users. A pipeline that costs $2 per query is not viable at scale. You optimize for these constraints from day one, not as an afterthought.
  • The simplest architecture that solves the problem is the best architecture. Direct prompting before RAG. RAG before fine-tuning. Fine-tuning before training from scratch. Each step up in complexity needs to justify itself with measured improvement on your eval suite.

Read the full file on GitHub · 71 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. 12d ago First seen · 71 lines · 72 tokens per session scan A 1245a69dd2b1

Subscribe to this mod's changes

ai-engineer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 2,129 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 2026-08-31.

Related

Other agents, from other repositories

data-engineer

ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…

travisjneuman/.claude · 76 tokens

ml-engineer

Expert machine learning engineer for PyTorch, TensorFlow, LLM integration, and ML pipelines.

travisjneuman/.claude · 22 tokens

ai-engineer

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.

HermeticOrmus/claude-code-game-development · 58 tokens

noise-chunker

Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.

Madhan230205/token-reducer · 25 tokens

doc-rag-builder

Scrapes documentation websites, builds high-fidelity RAG (Retrieval-Augmented Generation) systems with intelligent chunking and semantic indexing, and provides expert reader utility for querying latest documentation. Works with ANY documentation website (e.g., modelcontextprotocol.io, docs.anthropic.com, etc.).…

manutej/luxor-claude-marketplace · 0 tokens

ai-ml-engineer

Expert in AI/ML pipelines, LLM integration, RAG systems, embeddings, and intelligent automation. Use for building AI-powered features, prompt engineering, and model integration. Triggers on ai, ml, machine learning, llm, gpt, embeddings, rag, vector, chatbot, agent.

hoangatg/ai-agent-toolkit · 67 tokens