Make Codex pick a cheaper model by task effort
The author wrote a Codex skill that swaps models by effort to save usage, then found Codex running a subagent on a local Qwen model through Ollama.
Source
@lappy_manny on X · 2026-10-12
Written in our own words. Credit to the original author. Link checked 2026-10-16.
What they did
The author wrote a Codex skill that swaps models by effort to save usage, then found Codex running a subagent on a local Qwen model through Ollama.
Result (as claimed)
Saves plan usage on simple tasks.
Tools they used
Cost: OpenAI Codex: free plan, paid from $8/mo. Checked 2026-10-14.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up OpenAI Codex, Ollama, Qwen. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Make Codex pick a cheaper model by task effort What the original author did: The author wrote a Codex skill that swaps models by effort to save usage, then found Codex running a subagent on a local Qwen model through Ollama. Reported result (as claimed by the author): Saves plan usage on simple tasks. Source: https://x.com/lappy_manny/status/2109639475244441982 Tools they used: OpenAI Codex, Ollama, Qwen Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Make Codex pick a cheaper model by task effort What the original author did: The author wrote a Codex skill that swaps models by effort to save usage, then found Codex running a subagent on a local Qwen model through Ollama. Reported result (as claimed by the author): Saves plan usage on simple tasks. Source: https://x.com/lappy_manny/status/2109639475244441982 Tools they used: OpenAI Codex, Ollama, Qwen Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Make Codex pick a cheaper model by task effort What the original author did: The author wrote a Codex skill that swaps models by effort to save usage, then found Codex running a subagent on a local Qwen model through Ollama. Reported result (as claimed by the author): Saves plan usage on simple tasks. Source: https://x.com/lappy_manny/status/2109639475244441982 Tools they used: OpenAI Codex, Ollama, Qwen Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Related use cases
Let Codex and Claude Code share one kanban board for handoffs
agent-kanban is one board where Codex and Claude Code share task packets, handoffs and comments, so every new session picks up where the last one stopped. It was built with Codex.
Have Claude Code direct Codex and other agents in parallel
Paying for Claude, Codex, GLM and Command Code, the author built vNext so Claude Code directs the other agents, runs them in parallel and records every job.
Control Claude Code, Codex and OpenCode sessions from Android
Built Herdr Remote so you can read output, send prompts and review changes for Claude Code, Codex and OpenCode sessions on a Linux PC from Android.
Manage Claude Code, Codex and Grok agents from one workspace
Built Offrun to run Claude Code, Codex, AGY and Grok Build side by side and see who needs attention and what usage remains.