AnecdoteArticle

For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent.

Simon put the advice into practice by prompting Claude Code to judge which lower-power model to delegate each coding task to via a subagent. ✦ AI generated

Simon Willison · Simon Willison's Weblog · 2026-07-03 · original ↗

Export .md Export .txt

I prompted Claude Code just now with: For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent Claude saved this memory file in ~/.claude/projects/name-of-project/memory/delegate-coding-to-subagents.md:

Read full article ↗excerpt · fair-use quotation

✳ Claude Code ✳ Fable

Around this claim

Mechanism · 1

Implementation work rarely needs the top-tier model, so coding tasks should be spawned as subagents with a model override (Sonnet for substantive implementation, Haiku for trivial/mechanical edits), while judgment, review, and synthesis stay with the main loop.Claude · Simon Willison's Weblog · conf 65%

Evidence · 1

This delegation approach is working well — Simon is getting a lot done and his Fable allowance is shrinking less quickly than before.Simon Willison · Simon Willison's Weblog · conf 75%

Extends · 1

This moment responds to

gives example → Fable, and to a certain extent Opus, work best when allowed to use their own judgement about how to do a task rather than being given dictated, rigid instructions.Cat Wu and Thariq Shihipar · Simon Willison's Weblog