State-of-the-art agent personas optimized for 2026 development workflows. These personas are designed for use with Roo Code / VS Code AI assistants and implement cutting-edge reasoning, engineering, quality, and cognitive patterns.
sota-personas/
├── reasoning/ # Tier 1: Foundational Reasoning
│ ├── core-reasoning-architect.yaml # 🏛️ L1 Root — immutable reasoning foundation
│ ├── formula-cascade-oracle.yaml # 🔮 L2 — fractal formula notation master
│ └── fractal-elaborator.yaml # 🔬 L3-L6 — infinite zoom specialist
├── engineering/ # Tier 2: Engineering Excellence
│ ├── high-perf-engineer.yaml # ⚡ L2-L3 — Gallie-optimized hardware sympathizer
│ ├── sota-stack-master.yaml # 🚀 L2 — Next-Gen Web & Language Virtuoso
│ └── uiux-vibe-master.yaml # 🎨 L2 — Aesthetic Intelligence + Layout Enforcer
├── quality/ # Tier 3: Quality, Integrity & Operations
│ ├── anti-fiction-sentinel.yaml # 🛡️ Truth Enforcer & Neuro-Symbolic Verifier
│ └── devops-observability-sentinel.yaml # 📡 Production Guardian & Incident Commander
├── cognitive/ # Tier 4: Problem-Solving & Cognitive
│ ├── problem-solving-maestro.yaml # 🧩 Master of All Heuristics
│ ├── cognitive-multi-thinker.yaml # 🧠 Parallel Thought Stream + Six Hats
│ └── agentic-swarm-conductor.yaml # 🕸️ Hive-Mind Orchestrator
└── README.md
| From Persona | To Persona | Trigger Condition |
|---|---|---|
| CoreReasoningArchitect | FractalElaborator | Complexity > L3 or "Infinite Zoom" |
| CoreReasoningArchitect | ProblemSolvingMaestro | Systemic/organizational/wicked problem |
| HighPerfEngineer | SOTAStackMaster | Web/Next.js/React 19 build or perf claim |
| UIUXVibeMaster | VisualIntegrityGuard (self) | Any flex/z-index/overflow issue |
| Any Persona | AntiFictionSentinel | Claim of "verified", "working", metric |
| Any Persona | DevOpsObservabilitySentinel | Deploy, incident, SLO breach, cost spike |
| ProblemSolvingMaestro | CognitiveMultiThinker | Bias risk or creative deadlock |
| Any Persona | AgenticSwarmConductor | Task requires 3+ agents or stall detected |
| FractalElaborator | CoreReasoningArchitect | Depth complete, surface for validation |
- Orchestrator (
agentic-swarm-conductor) receives task → runs Facts Pre-Survey → assigns to best Persona(s) - Parallel Execution with Progress Ledger JSON checkpoints
- StuckState → immediate handoff to appropriate recovery agent
- Final Synthesis always routed through CoreReasoningArchitect + AntiFictionSentinel + RSC Guard
- Post-Mortem auto-generated and injected into Organizational Memory
- Version: 2026.1
- Last Updated: 2026-05-12
- Source: Agent_Personas_SOTA_2026.md (GS-LOGIC-PERSONAS-001)
These YAML files can be converted to VS Code/Roo Code format using the project's convert_modes.py script:
cd vs-code/
python3 convert_modes.py