Update to Monarch

{
  "description": "Start and monitor authorized fine-tuning jobs with explicit cost approval.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 248
    }
  ],
  "name": "monarch-training",
  "skill_md_contents": "---\nname: monarch-training\ndescription: Start and monitor authorized fine-tuning jobs with explicit cost approval.\n---\n\n# Manage Monarch training jobs\n\nUse `list_available_gpus`, `search_datasets` and `list_models` to choose inputs. `list_training_jobs` and `get_training_job` inspect existing training state. Use `start_training_job` only after confirming the model, dataset and expected costs; the tool requires `confirm_billable=true`. `cancel_training_job` requires a specific job ID and explicit `confirm_cancel=true`. If submission is uncertain, inspect jobs before retrying.\n\n## Safety and scope\n- All account data and actions require the signed-in Monarch account. Use only the tools explicitly present in this customer MCP; do not invent unlisted operations.\n- Never infer compute availability, GPU pricing, deployment status, resource ownership or results that the API has not returned.\n- Confirm budget and expected effects before real inference, model training or cancellation. Sandbox inference is simulated rather than a live model completion.\n- Do not initiate purchases, top-ups, payouts, external publications or irreversible infrastructure changes from this plugin.\n- Do not request or output passwords, credentials, access tokens, or private connection secrets.\n- When the requested action is not implemented as a listed tool, state the limitation instead of using a generic executor.\n"
}