---
title: "agentic-bundle-aas-agent-mcp-builder"
description: "Portable skills-only \"AAS Agent & MCP Builder\" plugin from Agentic Awesome Skills."
canonical: https://agentpluginsdirectory.com/plugins/agentic-bundle-aas-agent-mcp-builder--costrict-plugins-repo
last-updated: 2026-10-21
---

# agentic-bundle-aas-agent-mcp-builder
Portable skills-only "AAS Agent & MCP Builder" plugin from Agentic Awesome Skills.
- Slug: agentic-bundle-aas-agent-mcp-builder--costrict-plugins-repo
- Publisher: sickn33 and contributors
- Repository: https://github.com/costrict-plugins-repo/sickn33-agentic-awesome-skills-agentic-bundle-aas-agent-mcp-builder
- Manifest: plugin.json
- Version: 19.11.0
- License: MIT
- Category (editorial): agent-tooling
- Skills: 17 (agent-evaluation-reporting, agent-evaluation, agent-harness-fault-injection, agent-memory-systems, ai-agents-architect, context-window-management, langfuse, langgraph, llm-app-patterns, llm-evaluation, mcp-builder, mcp-tool-developer, prompt-caching, prompt-engineering, rag-engineer, rag-implementation, skill-security-audit)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-01
- Repository last pushed: 2026-10-20
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/agentic-bundle-aas-agent-mcp-builder--costrict-plugins-repo
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- agent-evaluation-reporting
- agent-evaluation: Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring, where even top agents achieve less than 50% on real-world benchmarks
- agent-harness-fault-injection
- agent-memory-systems
- ai-agents-architect: Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
- context-window-management: Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot
- langfuse: Expert in Langfuse: the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production.
- langgraph: Expert in LangGraph: the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern.
- llm-app-patterns: Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices.
- llm-evaluation
- mcp-builder: Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
- mcp-tool-developer: Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.
- prompt-caching
- prompt-engineering: Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
- rag-engineer: Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.
- rag-implementation
- skill-security-audit

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.