verdict

Claude Code QA agent with memory, plus a read-only MCP server (verdict-qa-mcp on PyPI): baseline → delta runs (NEW/REGRESSED), a fact harness so the model judges while the system measures, signed run history, flaky quarantine with expiry, and an exit-code release gate for CI. Ships six scored eval fixtures — misses published.

{
  "mcpServers": {
    "verdict": {
      "command": "uvx",
      "args": [
        "verdict"
      ]
    }
  }
}

claude mcp add verdict uvx verdict

{
  "mcpServers": {
    "verdict": {
      "command": "uvx",
      "args": [
        "verdict"
      ]
    }
  }
}