Better Quality/Cost Setup of Default Models for Subagents as of Fall 2026

A developer's late September–early October 2026 survey of GPT and Anthropic models found subagent token usage runs 15–35% of a main agent session's usage, and recommends GPT-6 Luna (xhigh) for explore, GPT-6 Luna (high) for task, Claude Opus 5.5 (high) for general-purpose, GPT-6.1 Sol (xhigh) for rubber-duck and research, GPT-6.1 Sol (medium) for code-review, and GPT-6.1 Sol (high) for security-review as default GitHub Copilot CLI subagent settings. The author notes switching general-purpose from Claude to Sol 6.1 High yields further token savings at a small loss of analytical thinking, and shares a copy-paste-ready prompt to apply the settings.

Even hyperscalers are watching their token spend nowdays, and Microsoft is no exception. Everybody know model of the agent session matters. However, fewer are aware about default models settings for specialized subagents. Harnesses use them when spininng up subagents for: 1 specialized tasks research, tests run, review, etc. 2 different parts of the agentic loop in commands like /goal in Codex or autopilot mode in Github Copilot 3 multi-agents execution modes like /fleet in Github Copilot. Wrong deafult model or effort level makes your agents less smart and more constly. I’ve checked the metrics of my typical sessions: subagents token usage varies in 15–35% range of the main session token usage. The number is even higher for /fleet or /goal use-cases. So, better default models can make a real difference. I’ve made research for the latest GPT and Anthropic models for my team: Opus 5.5, Astra 6, Sol 6.1, Luna 6, and Sonnet 5.5 to find out better cost-effective model and effort for every common agent/agent task type. Sharing the results in super short format here for community. Copy-paste-ready prompt with settings for Github Copilot is the end of the text. Data freshness: late September–early October 2026. The AI landscape changes every week. Feel free to copy as is and prompt your agent to set as default. Update my user-level Copilot CLI subagent settings. Change only these agents, keep everything else, and show me the result as a table. explore — GPT‑6 Luna xhigh task — GPT‑6 Luna high general-purpose — Claude Opus 5.5 high rubber-duck — GPT‑6.1 Sol xhigh code-review — GPT‑6.1 Sol medium research — GPT‑6.1 Sol xhigh security-review — GPT‑6.1 Sol high Change general-purpose from Claude to Sol 6.1 High if need even more token savings. However, it comes with a little loss of analytical thinking. Better Quality/Cost Setup of Default Models for Subagents as of Fall 2026 https://blog.devgenius.io/default-agent-model-setup-for-better-quality-cost-at-sep-oct-2026-1a66569670da was originally published in Dev Genius https://blog.devgenius.io on Medium, where people are continuing the conversation by highlighting and responding to this story.