Claude Code has one bad habit: its built-in Explore and Plan subagents run on your main…
This is a vibe coding post classified by AGK Intelligence as Coding agents (a workflow), kept by the Vibe Coding Radar because it carries real work, not commentary.
Claude Code has one bad habit: its built-in Explore and Plan subagents run on your main model by default. If your main model is Opus, all that file digging and code searching 𝗯𝘂𝗿𝗻𝘀 𝘆𝗼𝘂𝗿 𝗢𝗽𝘂𝘀 𝗾𝘂𝗼𝘁𝗮. If your quota is limited and you still want the best results, have Sonnet write, Haiku search, and Opus review. CLAUDE_CODE_SUBAGENT_MODEL=haiku CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1 claude --model sonnet --advisor opus Setting only CLAUDE_CODE_SUBAGENT_MODEL=haiku 𝗱𝗼𝗲𝘀𝗻'𝘁 𝘁𝗼𝘂𝗰𝗵 𝗘𝘅𝗽𝗹𝗼𝗿𝗲 𝗮𝗻𝗱 𝗣𝗹𝗮𝗻. You need FORCE=1 to switch every subagent to Haiku, though it also overrides the model set in your own a
Posted by Vox (27.9k followers) 2 days ago · 78 likes · 6.2k views · view the original post on X. Kept by the Vibe Coding Radar as Coding agents.
More vibe coding work like this
- This week at Entelligence, we launched Entelligence Memory: one shared memory for every… — @EntelligenceAI
- Changing coding agents? Teams Plan in @DevinAI is 50% off for three months! — @Chris_Wozniczek
- Kimi K3.1 Pro is now live on @akashnetAI. — @akashnet
- Here's 4 steps to run an uncensored AI on your own GPU for $0: — @DeRonin_
- just farm, built in 5 weeks with opus 5.5 and unity 6 per the post. the dev's rule is… — @0xSpikez
- Can coding agents replace traditional 3D vision pipelines and build a entire interactive… — @EinsiaAI
- 🚀 Work across multiple agents, keep your favorite canvases close, and customize how you… — @code
- Claude Code agents recently turned an ordinary academic reading list into an interactive… — @Bober_smart
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 17:42 UTC. Full method.