{
  "ocm": "1",
  "id": "gnoverse-gno-mcp-playground",
  "kind": "skill",
  "name": "playground",
  "description": "This is the agent-e2e harness: a host-side **driver** Claude QAs a containerized Claude+gnomcp+gno-skill (the AUT) scenario by scenario against an in-memory simnet.",
  "publisher": "gnoverse",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "This is the agent-e2e harness: a host-side **driver** Claude QAs a containerized Claude+gnomcp+gno-skill (the AUT) scenario by scenario against an in-memory simnet."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-agents",
      "repository": "https://github.com/gnoverse/gno-mcp",
      "path": "playground/AGENTS.md",
      "ref": "3aa21865e3bbc26de53a979086a5e068d920cd42",
      "url": "https://github.com/gnoverse/gno-mcp/blob/3aa21865e3bbc26de53a979086a5e068d920cd42/playground/AGENTS.md",
      "key": "gnoverse/gno-mcp/playground/AGENTS.md"
    }
  },
  "instructions": "# AGENTS.md — working on the playground harness\n\nThis is the agent-e2e harness: a host-side **driver** Claude QAs a containerized\nClaude+gnomcp+gno-skill (the AUT) scenario by scenario against an in-memory simnet.\n\n**Load the `playground-driver` skill before doing anything here** — running or debugging e2e,\nauthoring or editing scenarios, or changing the driver. It carries the wire protocol, judging\nrules, scenario format, and verify toolkit; without it you will get the mechanics wrong. It\nlives at `.claude/skills/playground-driver/` (also linked from the repo-root `.claude/skills/`,\nso it sur",
  "cost": {
    "context_tokens": 191
  }
}