skills.rest
JFrangel
JFrangelCOMMUNITY
Explore all skills by this author →
GitHub

agent-architect

Design and orchestrate scalable AI agent ecosystems with identity management and safe handoffs.

Updated Mar 8, 2026
Search Tags:#multi-agent#ai-architecture#context-engineering#spec-driven-development#agent-harness#cream#identity-framework
One-click install
npx skills add https://github.com/JFrangel/agents --skill agent-architect-jfrangel
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-architect
Source: https://github.com/JFrangel/agents/tree/main/skills/arquitectura-agentes
Command: npx skills add https://github.com/JFrangel/agents --skill agent-architect-jfrangel

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Designs and orchestrates scalable AI agent ecosystems, providing a robust harness to control multi-agent workflows, identity anchoring, and safe handoffs.

Core Features & Use Cases

  • Agent Harness design: defines identities, tools, and guardrails for supervisor-to-worker pipelines.
  • Context management: applies CREAM caching and memory auditing to prevent context rot and optimize performance.
  • Handoff protocols: supports A2A and LangGraph-based handoffs for typed, secure inter-agent communication; MCP tool definitions enable standardized tool usage.
  • Spec-Driven Development: enforces SDDr before implementation to ensure compliance and traceability.
  • Identity framework: static identity files (USER.md, SOUL.md, IDENTITY.md) anchor agent behavior.
  • Safety and governance: stop hooks, action gates, and security checks are baked into workflows.

Quick Start

Create your Agent Harness for a target task by defining identities (USER/SOUL/IDENTITY), selecting MCP tools, and preparing an SDD, then run the harness to start the workflow.

Frequently Asked Questions about agent-architect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a scalable multi-agent architecture for enterprise workflows?▼

Handoffs in multi-agent systems are managed using A2A protocols and LangGraph-based communication, secured by action gates and security checks to ensure typed, safe inter-agent transitions during complex workflow execution.

What is Spec-Driven Development for AI agents?▼

Context rot in AI agents is prevented by applying CREAM caching and memory auditing strategies, which optimize performance and maintain context integrity across multi-agent workflows with context-rotation safeguards.

Can I use LangGraph handoffs for secure inter-agent communication?▼

This approach suits enterprise-scale multi-agent workflows requiring identity management, caching strategies, and safe handoffs, specifically when modular architecture, explicit stop-hooks, and Spec-Driven Development compliance are necessary.

When do I need stop-hooks and context-rotation safeguards in multi-agent systems?▼

To start, define agent identities like USER.md, SOUL.md, and IDENTITY.md, select appropriate MCP tools, prepare an SDD specification, and execute the harness to initiate the multi-agent workflow.

Related Skills

Explore More Software Engineering Skills→
kyle-deprowkyle-deprow

openclaw-persona-identity

Design OpenClaw agent personas using six bootstrap Markdown files.

Community
Advanced
nexus-labs-automationnexus-labs-automation
7

multi-agent-coordination

Trace supervisor-worker handoffs and hierarchies in multi-agent workflows.

Official
Advanced
JFrangelJFrangel

arquitectura-agentes

Design scalable agent systems with Agent Harness and Context Engineering.

Community
Advanced
AesopScottAesopScott
1

multi-agent-orchestration

Configure runtime topology, routing, and handoff protocols for multi-agent systems.

Community
Advanced