Claude Code’s system prompt shrank 80% as Fable works better with lighter prompts
emollick · x · 2026-07-21
A notable prompt-engineering takeaway for Claude/Fable: treat stronger and weaker models differently. Skills that work on Opus can make Fable worse, and piling on negative instructions can also hurt output.
The thread also notes that Claude Code’s system prompt recently shrank by 80%, reinforcing the idea that lighter prompting can be better for newer model behavior.
Related event: Claude Code System Prompt Reduced by 80%(4 posts)→
More from coding & agent
- Chaining dependent MCP tool calls: no rollback, duplicate risk — agentrsdg · 2026-09-11
- DeepMind-led paper makes design docs the source of truth, code disposable — SMART regenerates in 1.5-3h for ~$100 — Roger_M_Taylor · 2026-09-11
- Agent-built classifier labels 192k docs for $0.70 vs $13-26 with frontier LLMs — vanstriendaniel · 2026-09-11
- MathModelAgent gains traction: auto-solves math modeling and writes a submission-ready paper — jihe520 · 2026-09-11
- alphaXiv open-sources OpenResearch to run parallel research agents with any model — alphaXiv · 2026-09-11
- DeskcommCRM: open-source AI sales CRM with native agents and WhatsApp hits 1k stars — melgarafael · 2026-09-11