claude-code-mcp-harness

Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and ledgers, independently validate output, and send bounded fix/review runs through the Codex-Claude harness.