7 Practical Tips to Save Claude Code Tokens: Field Insights from Anthropic Engineers
A battle-tested guide to optimizing token usage in Claude Code, based on internal experiments by Anthropic engineers. Covers prompt cache preservation, /clear a
#PromptCaching
TAU-HOME.COM stories tagged PromptCaching.
Claude Code Tip: Give Subagents Waiting on Tests or Builds a 1-Hour Cache
A practical guide to selectively configuring 1-hour prompt caching (cacheTtl: 1h) on Claude Code subagents that idle during long test runs or builds, preventing
OpenAI Releases Official Model Guide for GPT-6 Family: Role Specialization, Caching, and Latency Optimization
OpenAI has published an official practical guide for the GPT-6 model family, detailing role specialization across Astra, Sol, and Luna, reasoning effort control
Preventing Token Spikes in Claude Code: Managing Prompt Cache Expiration with /clear
Why resuming idle Claude Code sessions triggers massive uncached token usage due to KV cache expiration, and how using /clear protects your usage limits.
How to Cut AI API Bills by 60% When Switching to Claude Opus 5.5: A 4-Step Settings Guide
A practical guide to cutting Claude Opus 5.5 API costs by up to 61%, moving beyond the basic 24% model discount through token pruning, effort tuning, and aggres