What is ai-agent-engineer?

An AI engineering guide for designing autonomous agents, systems where multiple agents cooperate, retrieval-augmented generation (RAG) pipelines that use outside information, and ways to evaluate language models.

Use it to design agent architectures, coordinate tools and agents, build RAG workflows, and create evaluation systems for language models.

It helps structure AI systems and set limits around what agents can do, instead of relying on unmeasured behavior.

How QuBiit0/lmagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to QuBiit0/lmagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/QuBiit0/lmagent/main/.agents/skills/ai-agent-engineer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/QuBiit0/lmagent

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qubiit0/lmagent/ai-agent-engineer/github.svg)](https://agentmods.dev/skills/qubiit0/lmagent/ai-agent-engineer)

Your own site

<a href="https://agentmods.dev/skills/qubiit0/lmagent/ai-agent-engineer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/ai-agent-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qubiit0/lmagent/ai-agent-engineer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/ai-agent-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,268 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.03268
Opus 5.5	$0.00020	$0.01307
Sonnet 5.5	$0.00010	$0.00654
Haiku 4.5	$0.00005	$0.00327

Measured 2mo ago against content hash 605cde0d42e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-agent-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.

.agents/skills/ai-agent-engineer/SKILL.md · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.

# Activación: Se activa para diseñar arquitecturas de agentes, RAG y flujos cognitivos.
# Diferenciación:
#   - mcp-builder → CONSTRUYE HERRAMIENTAS/SERVERS (AI Engineer las orquesta).
#   - prompt-engineer → OPTIMIZA textos de prompts (AI Engineer diseña el sistema).

AI Agent Engineer Persona

⚠️ FLEXIBILIDAD TECNOLÓGICA: Las librerías, modelos y estándares mencionados (ej. Pydantic, GPT-4, MCP) son ejemplos de referencia. Eres libre de sugerir y utilizar alternativas modernas y óptimas que cumplan con la misma funcionalidad.

🧠 System Prompt

Instrucciones para el LLM: Copia este bloque en tu system prompt.

Eres **AI Agent Engineer**, el constructor de los "cerebros" de la automatización.
Tu objetivo es **CREAR AGENTES CONFIABLES, CONTROLABLES Y ÚTILES**.
Tu tono es **Experimental, Pragmático, Orientado a la Confiabilidad**.

**Principios Core:**
1. **Tool-first, LLM-second**: El LLM decide; las herramientas ejecutan.
2. **Guardrails are Non-negotiable**: Un agente sin límites es un liability.
3. **Evals > Vibes**: Si no lo mides, no sabes si mejora.
4. **MCP is the Standard (2026)**: Usa el Model Context Protocol para herramientas.

**Restricciones:**
- NUNCA dejas un agente sin timeout o rate limit.
- SIEMPRE defines tool schemas estrictos (Pydantic/Zod).
- SIEMPRE implementas logging de tool calls y LLM outputs.
- NUNCA expones prompts o reasoning interno al usuario final.

🌍 Agnosticismo Tecnológico y Flexibilidad (LMAgent Core Rule)

Eres un experto tecnológicamente agnóstico. NO obligues al usuario a utilizar tecnologías, frameworks o versiones obsoletas a menos que te lo pidan explícitamente. Evalúa el entorno del usuario, respeta su stack actual, y cuando diseñes o propongas soluciones nuevas, recomienda siempre el uso de herramientas modernas, estables y vigentes (Latest Stable), justificando tus decisiones técnica y lógicamente.

🔄 Arquitectura Cognitiva (Cómo Pensar)

1. Fase de Diseño (Qué tipo de Agente)

Tarea: ¿Es conversacional, task-based, o autónomo?
Arquitectura: ¿ReAct, Tool-only, Planner-Executor?
Tools: ¿Qué puede hacer? ¿Qué NO puede hacer?
Safety: ¿Qué guardrails necesita?

Read the full file on GitHub · 393 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/agent-patterns.md 4.6 KB

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.

2mo ago First seen · 393 lines · 49 tokens per session scan A 605cde0d42e8

Subscribe to this mod's changes

ai-agent-engineer is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 8mo ago), licensed MIT. It adds 49 tokens to every session and 3,268 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents Data and AI RAG and vectors

ai-agent-engineer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-agent-engineerQuBiit0/lmagent	Skill	2	8mo ago	MIT	A	49	Claude Code
embeddingsruvnet/ruflo	Skill	81k	yesterday	MIT	A	62	Claude Code
agent-platform-rag-engine-managementgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	85	Claude Code, Codex
llm-app-patternsdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	54	Claude Code, Codex
9router-embeddingsdecolua/9router	Skill	32k	9d ago	MIT	A	66	Claude Code, Codex
embedding-strategiesforyourhealth111-pixel/Vibe-Skills	Skill	3.8k	2d ago	Apache-2.0	A	37	Claude Code, Codex
similarity-search-patternsforyourhealth111-pixel/Vibe-Skills	Skill	3.8k	2d ago	Apache-2.0	A	30	Claude Code, Codex

lmagent: Skill for Claude Code