LodeHQ
AI news for people who shipFree, by email

DevOps · thenewstack.io · Tuesday, 18 August 2026

Anthropic slashes Claude Code skill context cost from 200K to 25K tokens

A bundled Claude Code skill was silently burning ~200,000 tokens before answering even a one-line question; v2.1.234 now loads docs on demand, cutting that to ~25,000, an 85% drop. Hidden context overhead degrades model quality and inflates cost, a reminder to measure AI pipeline token use.

Read the source: thenewstack.io ↗In the 18 August issue →