Fable's judgement

Simon Willison reported that instructing Claude Code to delegate coding tasks to lower-power subagents using its own judgment significantly improved efficiency and reduced token usage. The approach, inspired by tips from the Claude Code team and Jesse Vincent, allows the main model to focus on judgment-heavy work while subagents handle implementation.

One of the most interesting tips I got from the Fireside Chat https://www.ai.engineer/worldsfair/schedule?session=asn slot 2026 06 30 main stage 1230 2026 06 08t09 35 43 039z I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable and to a certain extent Opus use their own judgement rather than dictating how they should work. The example they gave was testing. You can tell Fable "only use automated testing for larger features, don't update and run tests for small copy or design changes" - but it's better to just tell Fable to use its own judgement when deciding to write tests instead. Jesse Vincent just gave me a related tip to help avoid burning too many of those valuable Fable tokens in the few days we have left before the prices go up. Tell Fable to use other models for smaller tasks, applying its own judgement about which model to use. 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 : --- name: delegate-coding-to-subagents description: Simon wants coding tasks delegated to subagents running an appropriately lower-power model metadata: node type: memory type: feedback originSessionId: 30068d78-43a9-4fb1-bb29-9799e18c526a --- Stated by Simon on 2026-07-03: "For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent." Why:cost/efficiency — implementation work rarely needs the top-tier model; judgment, review, and synthesis stay with the main loop. How to apply:when a task in this project is primarily writing/editing code, spawn an Agent with a model override sonnet for substantive implementation, haiku for trivial/mechanical edits and a self-contained prompt; review the result in the main loop before committing. Design, auditing, data synthesis, and anything judgment-heavy stays in the main model. See also project-goals . So far it seems to be working well. I'm getting a ton of work done and my Fable allowance is shrinking less quickly than before. Tags: claude https://simonwillison.net/tags/claude , ai https://simonwillison.net/tags/ai , claude-code https://simonwillison.net/tags/claude-code , llms https://simonwillison.net/tags/llms , prompt-engineering https://simonwillison.net/tags/prompt-engineering , coding-agents https://simonwillison.net/tags/coding-agents , generative-ai https://simonwillison.net/tags/generative-ai , claude-mythos-fable https://simonwillison.net/tags/claude-mythos-fable , anthropic https://simonwillison.net/tags/anthropic