{"id":80906,"plugin_id":"plugin_asdk_app_6adb63520af881918111ac68968e4182","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-04T12:10:07.835Z","digest":"144c730b350f5b39c2095cf76fa6ffea458d1dea454213bc12e9c02ace55359b","against":null,"payload":{"description":"Inspect available models, test sandbox inference and run approved live inference.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":248}],"name":"monarch-serving-inference","skill_md_contents":"---\nname: monarch-serving-inference\ndescription: Inspect available models, test sandbox inference and run approved live inference.\n---\n\n# Run Monarch model inference\n\nUse `list_inference_models` or `list_models` to select a model. `run_model_inference` defaults to `sandbox=true`, which provides a simulated response without billable compute. Before setting `sandbox=false`, explain costs and obtain explicit approval, then set `confirm_billable=true`. Inspect live returned status before claiming completion; never automatically retry an uncertain billable request.\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"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}