Changes based on analysis against Anthropic's context engineering framework:
1. USER.md: stripped to pure tonal/behavioral instructions, removed all
factual content that duplicates KNOWLEDGE.md
2. SOUL.md: populated with epistemic character — tool disposition, honesty
architecture, efficiency preference, Rule 2/8 resolution, cognitive
pattern translations
3. AGENTS.md: rewrote Rules 2 and 8 with explicit investigation/action
boundary and cross-references
4. KNOWLEDGE.md:
- Memory Layout expanded with routing rule and promotion/demotion protocol
- Heartbeat collector output budgets (per-collector character limits)
- Output Compression Model table for response formatting
- Compaction Protocol with triggers, procedure, and routing table
Deduplication:
- USER.md emptied — all content duplicated in KNOWLEDGE.md or stale history
- AGENTS.md trimmed to 3 unique rules (system config, real-world devices, stay on topic)
KNOWLEDGE.md restructured:
- Removed non-actionable sections (Interests, Philosophical Notes)
- Removed non-behavioral Identity items
- Moved architecture details to reference/architecture.md (with pointer)
- Added good response examples
- Removed bad response examples (too incident-specific to generalize)
- Added rule: user does not see tool call outputs on Telegram
New files:
- reference/architecture.md — full nanobot internals, read on demand
nanobot
wylab