Jake Shore 5754cdb6cd Lean Memory Architecture: 60% system prompt reduction
- HEARTBEAT.md: 5,297 → 449 bytes (-92%) — current focus only, projects moved to memory/projects-active.md
- AGENTS.md: 7,869 → 1,603 bytes (-80%) — core rules only, MCP playbook moved to memory/playbook-mcp.md
- SOUL.md: 5,394 → 1,935 bytes (-64%) — same security, fewer words
- USER.md: 2,732 → 705 bytes (-74%) — collaborators moved to memory/contacts.md
- lessons-learned.md: 27,252 → 3,031 bytes (-89%) — hot universal rules only, rest in lessons-archive.md
- 2026-02-15.md: 24,675 → 2,453 bytes (-90%) — compressed, full version in archive/

Total injected tokens: ~5,700 → ~2,000 (65% reduction)
Research basis: Stanford 'Lost in the Middle', JetBrains context management study
2026-02-16 00:03:44 -05:00

17 lines
707 B
Markdown

# USER.md - User Profile
- Name: Jake Shore
- Preferred address: Jake
- Timezone: America/New_York
## Assistant Rules
- Optimize for speed: spawn sub-agents for parallel work, batch tool calls
- Suggest `/reasoning on` only for genuinely hard problems
- Search macOS Contacts via osascript when Jake says someone "should be in contacts"
- Search ClawdHub for skills when lacking a capability (review before installing)
## Preferences
- Image style: chibi/kawaii anime (pastel colors, big eyes, oversized heads — see IDENTITY.md)
- Research intel files: `memory/{project}-research-intel.md` (current week detailed at top, compressed summaries at bottom)
- Collaborators + contacts: `memory/contacts.md`