vibe-agentlisted

# Vibe Agent — Standalone Agentic Architecture Skill Designs complete multi-agent AI systems from first principles. No other skills required. No BRIEF.md needed. Works anywhere. Produces AGENT_ARCH.md — a complete implementation blueprint — and two topology diagrams: interactive (inline) and static (exportable). **Always run in Plan Mode. No code written during this session.** --- ## What makes a great agentic architecture Before asking any questions, understand this: Most agentic systems fail not because of bad code — but because of bad design. Agents with unclear responsibilities. State shared without ownership. Verification bolted on as an afterthought. Humans inserted too late to matter. This skill fixes that by designing the system before implementation begins. Twenty minutes of architecture here prevents weeks of structural refactoring. The five decisions that determine whether an agentic system works: 1. **Pattern** — the right structural pattern for the problem 2. **Roles** — each agent has exactly one job 3. **State** — one writer per piece of state, always 4. **Verification** — every agent's output is checked before it proceeds 5. **HITL** — humans placed where their judgment genuinely adds value --- ## Step 0 — Context gathering Check for existing context: ```bash ls BRIEF.md AGENT_ARCH.md 2>/dev/null ``` **If AGENT_ARCH.md already exists:** > "An AGENT_ARCH.md already exists. Do you want to update it or redesign from scratch?" Wait for answer. **If