v10.5.2
thedotmack/claude-memv10.5.2Feb 26, 2026by thedotmack
AI Summary
This release updates documentation with the smart-explore benchmark report and refines the Smart Explore skill with benchmark-accurate token economics, new core principles, and improved guidance.
Key Highlights
- Published smart-explore benchmark report to public docs with methodology and data
- Added benchmark report to docs.json navigation under Best Practices
- Updated token economics with benchmark-accurate data (11-18x savings on exploration, 4-8x on file understanding)
- Added 'map first' core principle as decision heuristic for tool selection
- Added AST completeness guarantee to smart_unfold documentation
New Features
- Smart Explore skill updates
- Token economics recalibration
- Explore agent escalation guidance
Full Release Notes
## Smart Explore Benchmark Docs & Skill Update ### Documentation - Published smart-explore benchmark report to public docs — full A/B comparison with methodology, raw data tables, quality assessment, and decision framework - Added benchmark report to docs.json navigation under Best Practices ### Smart Explore Skill - Updated token economics with benchmark-accurate data (11-18x savings on exploration, 4-8x on file understanding) - Added "map first" core principle as decision heuristic for tool selection - Added AST completeness guarantee to smart_unfold documentation (never truncates, unlike Explore agents) - Added Explore agent escalation guidance for multi-file synthesis tasks - Updated smart_unfold token range from ~1-7k to ~400-2,100 based on measurements - Updated Explore agent token range from ~20-40k to ~39-59k based on measurements