AI Marketplaces Leaderboard

Adaptive Task Routing

ChatGPT plugin

Choose when to keep or switch

View in ChatGPT directory
Featured
No

not on the featured shelf

Movement

From our daily snapshots over the last 30 days.

Rank by placement

#5105of 6,02211places down24h—7d
#5,045#5,195#5,345#5,495Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

Rank in Productivity

#1077of 1,3714places down24h—7d
#1,059#1,103#1,147#1,191Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

In its category

How this plugin compares with others in the same category. Positions are counted within the category, not across the whole directory.

Productivity1,077th of 1,371 by placement
#PluginPosition7d
1074Speaker Delivery Profiler#5101—
1075OpenCompare#5103—
1076codex-sdlc#5104—
1077Adaptive Task RoutingThis page#5105—
1078Creator Publish Package#5106—
1079The Business Engineer#5110—
1080SQL Copilot#5112—

All 1,371 Productivity plugins

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.

Example prompts

  • “Use adaptive task routing before the next substantial phase.”

Skills

  • adaptive-task-routing

    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.

  • research-model-router

    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.

  • task-context-router

    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.

Categories
Made by
哲儀 朱 · Website
Sign-in
On Install
Availability
Available
Version
0.5.0
Keywords
agent-skills, context-routing, model-routing, reasoning-effort, agentic-workflows
Created
September 12, 2026