Fable 5.2 prompt-audit skill scans repos for stale instructions and overcautious rules
daniel_mac8 · x · 2026-11-11
danielmac8 released an installable /fable-5-2-prompt-audit skill that automates Anthropic's official Fable 5.2 prompting tips: it scans your repo for standing instructions to delegate to subagents, standing token budgets, harness instructions that edit earlier turns (Fable 5.2's "preserved thinking"), "treat the answer as done" prompts, think-less instructions, rigid style rules, and rules/notes/memories that make the model overly cautious — so you can clean up prompts for the new model's behavior.
Related event: Developer Open-Sources Fable 5.2 Prompt Audit Skill(3 posts)→
More from coding & agent
- Memgraph open-sources Context Graph: shared cross-session memory for Claude Code and Codex — JeremyCMorgan · 2026-11-11
- Fable 5.2-generated PR touches 3,000+ files, adds 441,926 lines in one change — cramforce · 2026-11-11
- Birthday gift: an AI agent emergently deployed the exact observability stack I wanted — sloppenheimer · 2026-11-11
- No Claude account? This DSH plugin lets you try Claude-style Whiteboards anyway — dotey · 2026-11-11
- Running 6 concurrent ds41-flash agents: persistent enough to need pi-durable coordination — dbreunig · 2026-11-11
- OpenAI roundup: architecture details of four GPT-Live voice agent builds — pbbakkum · 2026-11-11