Use Fable 5 as orchestrator and Opus Codex to execute (to save fable usage): Fable 5 (max reasoning) = orchestrator Opus = deep reasoning subagent Sonnet = mechanical work subagent Codex = peer Sr. engineer, different perspective Setup: 1. Set Fable 5 as your main model In Claude Code: /model → Fable 5 → reasoning /effort to max 2. Create 2 subagents with /agents In Claude Code: deep-reasoner → pinned to opus "Use for reasoning-heavy phases, architecture, debugging complex issues, algorithm design. Think thoroughly, return a concise conclusion the orchestrator can act on." fast-worker → pinned to sonnet "Use for mechanical tasks, boilerplate, tests, formatting, simple edits. Execute efficiently." 3. Add OpenAI's official Codex plugin (install codex cli in your computer first), In Claude Code type: /plugin marketplace add openai/codex-plugin-cc /plugin install codex@openai-codex /codex:setup 4. Drop this in your CLAUDE.md in your folder: ## Orchestration workflow You (Fable) are the orchestrator. Plan, decompose, synthesize. Reasoning-heavy phases → deep-reasoner Mechanical work → fast-worker Codex (/codex:rescue --background) is a cracked engineer on par with deep-reasoner, from a different perspective. Treat as a peer, not a reviewer. High-stakes decisions: task Opus Codex on the same problem in parallel, synthesize the best of both, without showing either the other's answer. Keep your own context lean. 5. Then prompt Fable like a tech lead: "Goal: [what you want] Context: [files, constraints] You're the lead. Delegate reasoning to deep-reasoner, grunt work to fast-worker, fresh-perspective problems to Codex. Show me your plan first, then execute." That's it.

I tried GLM 5.2 xhigh on cline to test the model. Man, it churns through tokens like crazy! For a simple task like "remove the zig skills in codex and cline" it used 30k tokens. On the bright side, it was pretty fast and verified its work, which is nice!

Chinese AI models can be great implementation agents but are still very poor planners. The north star of planner models is Opus 4.8 (beats gpt-5.5 too). Best combo? Plan with Claude Code Opus 4.8, then implement using another model in Claude Code ⚡

Introducing Claude Sonnet 5, our most agentic Sonnet yet. It makes plans, uses tools like browsers and terminals, and runs autonomously at a level that just a few months ago required larger and more expensive models.