Audit your agent skills for Fable 5.1 with /claude-api prompt-audit to prune stale rules
xiaohu · x · 2026-09-03
A practical tip for users trying Fable 5.1: run /claude-api prompt-audit to audit your skills. The command surfaces many redundant entries and flags rules written for older models that should be removed with the latest models.
Related event: Claude Skill Audit Tool Gains Traction as Developers Urged to Trim Skills(5 posts)→
More from coding & agent
- Jeff Dean mentions tokscale, the token usage tracker, delighting its creator — doodlestein · 2026-09-03
- Coding tool drama: t3 accused of lifting UI design from Codex desktop app — CtrlAltDwayne · 2026-09-03
- Eno Reyes: getting the most from models needs stateful intelligence allocation, not just routing — matanSF · 2026-09-03
- New open-source LLM test wrapper uses logging and check gates to curb model errors — Tyb0wls · 2026-09-03
- Meta's WhatsApp per-message pricing is breaking multi-turn agent economics — uriwa · 2026-09-03
- The case for a minimal agent harness: thin loop, no plugins, skills as plain content — uriwa · 2026-09-03