Config Trick in CLAUDE.md Claimed to Slash Fable Token Usage by 90%
jdjohnson · x · 2026-07-04
A configuration trick to drastically reduce Claude Fable model token consumption is shared: adding a directive like "You are primarily used for..." in CLAUDE.md guides Fable to respond more concisely. This is said to cut token usage by roughly 90%, making it ideal for controlling costs in long conversations and agent workflows.
More from coding & agent
- 'My intelligence stack': developer splits AI coding work across Opus 5.5, Fable and Astra with human review gates — sh_reya · 2026-10-27
- Baseten webinar: evaluate open models for coding agents by benchmarking on your own merged PRs — baseten · 2026-10-27
- Thorsten Ball on working with agents: run more evals, automate everything, use the best models — omarsar0 · 2026-10-27
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- BELL: Open-Source Stack Combines Browserbase, Eve, iMessage and Stripe Link for Personal Agents — jeff_weinstein · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27