lmagent: Skill for Claude Code

.agents/skills/ai-agent-engineer/SKILL.md

ai-agent-engineer is a skill for Claude Code from QuBiit0/lmagent. It costs 49 tokens per session (3,268 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Use it to design agent architectures, coordinate tools and agents, build RAG workflows, and create evaluation systems for language models.
Why use it?
It helps structure AI systems and set limits around what agents can do, instead of relying on unmeasured behavior.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Gemini CLI.

This is QuBiit0/lmagent's own configuration. It tells Claude Code how to work on lmagent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lmagent configures →

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.

agentmods badge for ai-agent-engineer

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.

agentmods 80×15 button for ai-agent-engineer

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.03268
Opus 5 $0.00024 $0.01634
Sonnet 5 $0.00010 $0.00654
Haiku 4.5 $0.00005 $0.00327

Measured 9d ago against content hash 605cde0d42e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

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. 9d 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 6mo ago), licensed MIT. It adds 49 tokens to every session and 3,268 once invoked, about $0.0002 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 skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

azure-search-documents-dotnet

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…

microsoft/skills · 102 tokens

browserwing-admin

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

MemTensor/MemOS · 47 tokens

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

foryourhealth111-pixel/Vibe-Skills · 30 tokens