For AI agents: the complete documentation index is available at https://scriptedalchemy.github.io/agent-bundle/llms.txt, the full documentation bundle is available at https://scriptedalchemy.github.io/agent-bundle/llms-full.txt, and this page is available as Markdown at https://scriptedalchemy.github.io/agent-bundle/api/functions/eval.runClaudeSemanticGrader.md.
agent-bundle
  • English

      • Function: runClaudeSemanticGrader()

      runClaudeSemanticGrader(options): Promise<ClaudeSemanticGraderRun>

      Uses the already-preflighted Claude CLI as a model grader. The command and request are server-owned: it receives no plugin directory, hook flags, authored command, or provider credentials.

      Parameters

      options

      RunClaudeSemanticGraderOptions

      Returns

      Promise<ClaudeSemanticGraderRun>