{
  "name": "honeybadge/harbor",
  "version": "0.1.0",
  "private": false,
  "summary": "Framework for AI agent evaluation in containerized environments. Use when: (1) Running agent evaluations with `harbor run` against benchmarks (SWE-Bench, Terminal-Bench, Aider Polyglot, etc.), (2) Creating custom benchmark tasks with Dockerfile, instruction.md, solution, and tests, (3) Building adapters to convert existing benchmarks to Harbor format, (4) Implementing custom agents extending BaseAgent or BaseInstalledAgent, (5) Scaling evaluations to cloud providers (Daytona, Modal, E2B), (6) Exporting traces for RL/SFT training, (7) Debugging Harbor runs or inspecting package internals.",
  "skills": {
    "harbor": {
      "path": "SKILL.md"
    }
  }
}