Run dynamic, multi-agent workflow scripts — agent(), parallel(), pipeline() — over real coding agents (Claude Code and OpenAI Codex), with deterministic journaling, resume, token budgets, and git-worktree isolation.
Enables AI agents to execute multi-step Standard Operating Procedures step by step, with enforcement of completion at each step, making LLM behavior predictable and auditable.
Enforces structured, evidence-guided software engineering tasks with cognitive actions (investigate, plan, verify, remember) and persistent state for LLM-based coding agents.
Provides a specification-driven workflow layer for AI-assisted coding, enabling agents to follow an explicit 11-phase feature workflow with checkpoints, artifacts, and quality gates.