{"id":28940,"plugin_id":"plugins_6aa58f86c9588191a1301728fbff6c46","kind":"catalog","collection_source":null,"comparison_source":null,"observed_at":"2026-10-09T00:00:01.850Z","digest":"a458c5f12922ba60e175feda925317662ca4871fac6ca43f028f57a5d423b05c","against":4734,"payload":{"canonical_app_id":null,"connector_id":null,"created_at":"2026-09-12T17:51:34.640367Z","discoverability":"LISTED","id":"plugins_6aa58f86c9588191a1301728fbff6c46","is_template":false,"name":"adaptive-task-routing","release":{"app_ids":[],"app_manifest":null,"app_templates":[],"description":"Recommend what to do next at task boundaries: keep, hand off, or change AI settings when worthwhile.","display_name":"Adaptive Task Routing","id":"pluginrel_21dc8e13c6888191a5ef5d9fe103bee3","interface":{"brand_color":null,"capabilities":[],"category":"Productivity","composer_icon_dark_url":null,"composer_icon_url":"https://files.openai.com/content?id=file_00000000d91c8209bba01cb67427b459","default_prompt":"Use adaptive task routing before the next substantial phase.","default_prompts":["Use adaptive task routing before the next substantial phase."],"developer_name":"哲儀 朱","logo_url":"https://files.openai.com/content?id=file_00000000e68881fd956c5d092aee5b23","logo_url_dark":null,"long_description":"Adaptive Task Routing assesses conversation, model and reasoning resources at meaningful task boundaries. It shows the action to take now before a concise reason, distinguishing task-fit settings from whether a switch is worthwhile. Keeping a suitable setup and retaining provisionally under uncertainty are separate outcomes. Default ask confirms proposed changes or material blockers; retention and nonblocking defer continue only already authorized work. Plan-only requests never authorize implementation. Auto applies only justified, authorized, callable and verifiable changes. Compact uses a plain heading and one conversation sentence. Verified keep shows only the observed current AI; detailed adds task-fit alternatives, minimum settings and upgrade rationale. Ordinary changes ask only about the target setting. Actual savings and reliability improvements require evidence.","plugin_category_id":"productivity","privacy_policy_url":null,"screenshot_urls":[],"short_description":"Choose when to keep or switch","terms_of_service_url":null,"website_url":"https://github.com/zyzdev/adaptive-task-routing"},"keywords":["agent-skills","context-routing","model-routing","reasoning-effort","agentic-workflows"],"onboarding_skill_name":null,"requires_local_executor":false,"skills":[{"description":"Primary routing entrypoint for substantial multi-step coding, debugging, architecture, validation, research, analysis, audits, and scans, and for conversational commands that inspect or change both routing modes. Use after a requested analysis or plan identifies actionable next work, or before executing a substantial phase, when both conversation context and model/reasoning should be assessed. Prefer this coordinator over either child router for general tasks. Skip brief explanations, status checks, tiny edits, and ordinary plugin-only questions.","interface":{"brand_color":null,"default_prompt":null,"display_name":"adaptive-task-routing","icon_large_url":null,"icon_small_url":null,"iconography":"hierarchy","short_description":"Primary routing entrypoint for substantial multi-step coding, debugging, architecture, validation, research, analysis, audits, and scans, and for conversational commands that inspect or change both routing modes. Use after a requested analysis or plan identifies actionable next work, or before executing a substantial phase, when both conversation context and model/reasoning should be assessed. Prefer this coordinator over either child router for general tasks. Skip brief explanations, status checks, tiny edits, and ordinary plugin-only questions."},"name":"adaptive-task-routing","plugin_release_skill_id":"pluginrsk_6aa58f89ee188191bfac7b14b1821de1"},{"description":"Model-only child router for substantial coding, debugging, architecture, validation, research, or analysis, and for conversational inspection or changes of the model-routing mode. Use when the user explicitly asks only for model/reasoning advice or mode control, when adaptive-task-routing delegates with a resolved context, or at a later model-only phase transition. For a general task needing both context and model routing, dispatch to adaptive-task-routing instead. Skip ordinary chat and tiny operations; do not choose context.","interface":{"brand_color":null,"default_prompt":null,"display_name":"research-model-router","icon_large_url":null,"icon_small_url":null,"iconography":"code","short_description":"Model-only child router for substantial coding, debugging, architecture, validation, research, or analysis, and for conversational inspection or changes of the model-routing mode. Use when the user explicitly asks only for model/reasoning advice or mode control, when adaptive-task-routing delegates with a resolved context, or at a later model-only phase transition. For a general task needing both context and model routing, dispatch to adaptive-task-routing instead. Skip ordinary chat and tiny operations; do not choose context."},"name":"research-model-router","plugin_release_skill_id":"pluginrsk_6aa58f899f0c8191803977c31731e3f9"},{"description":"Context-only child router that chooses CURRENT, HANDOFF, or CLEAN and handles conversational inspection or changes of the context-routing mode. Use when the user explicitly asks only for context advice or mode control, or when adaptive-task-routing delegates. For a general substantial task needing both context and model routing, dispatch to adaptive-task-routing instead. Do not choose a model or reasoning effort.","interface":{"brand_color":null,"default_prompt":null,"display_name":"task-context-router","icon_large_url":null,"icon_small_url":null,"iconography":"hierarchy","short_description":"Context-only child router that chooses CURRENT, HANDOFF, or CLEAN and handles conversational inspection or changes of the context-routing mode. Use when the user explicitly asks only for context advice or mode control, or when adaptive-task-routing delegates. For a general substantial task needing both context and model routing, dispatch to adaptive-task-routing instead. Do not choose a model or reasoning effort."},"name":"task-context-router","plugin_release_skill_id":"pluginrsk_6aa58f89a524819198bd26a24d139184"}],"version":"0.5.0"},"scope":"GLOBAL","status":"ENABLED"},"changes":[{"path":"/discoverability","type":"changed","before":"UNLISTED","after":"LISTED"}],"summary":"Fields changed: 1. /discoverability.","summary_kind":"deterministic","summary_metadata":{}}