{
  "name": "rug-agentic-workflow",
  "description": "Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.",
  "version": "1.0.0",
  "author": {
    "name": "Awesome Copilot Community"
  },
  "repository": "https://github.com/github/awesome-copilot",
  "license": "MIT",
  "tags": [
    "agentic-workflow",
    "orchestration",
    "subagents",
    "software-engineering",
    "qa"
  ],
  "items": [
    {
      "path": "agents/rug-orchestrator.agent.md",
      "kind": "agent",
      "usage": "recommended\n\nThis workflow is designed as a coordinated trio:\n- `RUG` orchestrates decomposition, delegation, and validation loops.\n- `SWE` executes implementation tasks.\n- `QA` validates requirements, edge cases, and regressions.\n\nTypical usage:\n1. Start with `RUG` for multi-step tasks.\n2. Let `RUG` delegate coding to `SWE`.\n3. Let `RUG` delegate verification to `QA`.\n\nBest results:\n- Keep each delegated task narrowly scoped.\n- Require explicit acceptance criteria per task.\n- Run a final cross-task validation pass before completion."
    },
    {
      "path": "agents/swe-subagent.agent.md",
      "kind": "agent"
    },
    {
      "path": "agents/qa-subagent.agent.md",
      "kind": "agent"
    }
  ]
}