Context-Management
- 2026-07-26 | Prompt Caching: Cut AI Agent Token Costs Learn how prompt caching changes LLM token costs, why coding agents resend context, what compaction can waste, and how to measure Codex, Claude Code, and OpenCode.
- 2026-02-03 | Verify Codex Token-Usage and Caching Claims A dated verification ledger for Codex token usage, prompt caching, compaction rereads, OpenCode comparisons, usage incidents, and reset claims.