3 tagged cache optimization, measured the same way as everything else here.
lokikill123/codex-token-skills
Skill Claude CodeCodex
Persistent global memory across conversations. Read memory file at start of every conversation, write important context during conversation so it survives context compression. Use ALWAYS. Triggered automatically.
lokikill123/codex-token-skills
Skill Claude CodeCodex
Minimize token consumption & maximize prompt cache hit rate. Use when user asks to save tokens, reduce cost, improve cache hit rate, or be more concise.
Skill Claude CodeCodex
Conducts deep, multi-angle research using the agentcache library's parallel cache-safe forks. Use when the user asks to research a complex topic, investigate architecture trade-offs, or synthesize information from multiple angles.