Open-source script measures whether raising Claude Code subagent prompt cache TTL from 5m to 1h pays off
daniel_mac8 · x · 2026-10-11
danielmac8 released cachegapcheck.py, a read-only script that scans Claude Code transcripts (/.claude/projects//.l) for subagent (sidechain) requests and measures gaps to estimate whether raising subagentPromptCacheTtl from 5 minutes to 1 hour is worth it. Useful for heavy Claude Code users optimizing token spend with multi-agent workflows.
More from coding & agent
- Dev builds lightning-fast audio + traces query harness for AI agent debugging — julianweisser · 2026-10-11
- Jeff Weinstein praises Instinct's rapidly evolving agent messaging UX — jeff_weinstein · 2026-10-11
- ascii.rest launches image-to-ASCII, SVG export and shadcn registry for animated ASCII art — sull · 2026-10-11
- 20 open-source tools for AI agent security, organized into 6 categories — MaryamMiradi · 2026-10-11
- Vibe coding only works if you already know how to code, dev argues — prasenx · 2026-10-11
- AI ported g3sharp to Luau for a Roblox Studio mesh sculpting plugin — rms80 · 2026-10-11