Added

• Simple chronology check for old sessions — Prevents data loss when processing backlog
  • IF session_date < file_last_modified → append context
  • ELSE → normal update
  • Old sessions append missing context (don't replace existing)
  • New sessions update normally (can replace/restructure)
  • Works for: old backlog, multi-source overlap (Claude Code + OpenClaw), re-processing

Changed

• Simplified anti-conflict logic — Removed complex mode selection, deduplication checks
  • Clear IF/ELSE rule based on chronology
  • "When in doubt: append" principle
  • No content checking, no duplicate detection — just simple chronology
  • Clearer examples (old session appending after newer session processed)

See CHANGELOG.md for full details.

What's Changed

Refactored for Claude Code Plugin Best Practices

• Progressive disclosure: SKILL.md files split into concise instructions + reference.md for templates/tables (935→465 lines, -50% token usage)
• Skill naming fixed: brain:init→init, brain:process→process, brain:status→status (colons not valid per spec)
• Commands: /remember:init, /remember:process, /remember:status
• Removed invalid user-invocable frontmatter
• Removed redundant brain-session skill (hook handles it)

Also includes v1.5.0 (REMEMBER.md)

• User-editable REMEMBER.md for customizing brain behavior
• 7 optional sections: Capture Rules, Processing, Custom Types, Connections, Language, Templates, Notes
• Full documentation guide at docs/REMEMBER-md-guide.md

Full Changelog: v1.4.6...v1.5.1

What's New in v1.4.6

🎯 Major Features

• Knowledge Index Builder () — Scans your brain and outputs structured markdown tables (People, Projects, Areas, Notes, Tasks, Journal stats). Supports mode for hook injection.
• Knowledge-Aware Pipeline — Both /brain:process and brain dump now build a Resolution Map against the knowledge index before writing, preventing duplicates and enabling smart entity linking.
• Edit-First Updates — Skills now instruct the AI to use the Edit tool for surgical updates to existing files instead of rewriting entire files.
• Enhanced Pattern Detection — Persona now captures behavioral patterns: user corrections, stated preferences, repeated workflows, communication style, decision criteria, and code style.

⚡ Breaking Changes

• Complete skill rewrites — skills/process/SKILL.md and skills/remember/SKILL.md have been completely rewritten with clearer 5-step pipelines.
• Multilingual support — Task and persona detection now uses AI semantic analysis instead of regex patterns.

🔧 Technical Changes

• Hook now runs build_index.py --compact to inject full knowledge index (not just names) into brain dump context
• Reduced process skill from ~500 lines of mixed concerns to focused pipeline

Full Changelog: v1.4.5...v1.4.6

What's New

• Shared config resolver (config.py) for cleaner architecture
• Safe JSON construction in hooks (eliminates shell injection risks)
• Task routing: Focus (urgent) + Next Up (important) + project files (detailed)
• CONTRIBUTING.md with contribution guidelines
• GitHub Discussions enabled
• README optimized with competitive positioning (vs Mem.ai, Reflect)
• Friendly tone adjustments

Improvements

• Config resolution: 52 lines → 1 import
• Performance: -100ms per hook invocation
• Security: 3 shell injection vectors eliminated
• Backwards compatible 100%