initial: sovereign home — morrowind agent, skills, training-data, research, specs, notes, operational docs

Tracked: morrowind agent (py/cfg), skills/, training-data/, research/,
notes/, specs/, test-results/, metrics/, heartbeat/, briefings/,
memories/, skins/, hooks/, decisions.md, OPERATIONS.md, SOUL.md

Excluded: screenshots, PNGs, binaries, sessions, databases, secrets,
audio cache, timmy-config/ and timmy-telemetry/ (separate repos)

research/kimi-reports/TRIAGE.md

@@ -0,0 +1,49 @@
+# Kimi Deep Research Reports — Triage Summary
+Updated: 2026-03-19
+
+## Reports Ingested
+1. Payment-Gated AI Agent Economy Platform: Technical Architecture Report (48K chars)
+   - Architecture-level: WHAT to build, tradeoffs, protocol design
+   - Key sections: 5-phase payment flow, BOLT#11 metadata, 3 refund approaches, L402/macaroons, cloud infra, agent wallets, security, regulatory
+
+2. Sovereign AI Platform: Technical Implementation Report (50K chars)  
+   - Implementation-level: HOW to build it, production code, libraries
+   - Key sections: L402 FastAPI server, LND gRPC integration, cost estimation formulas, Nostr identity system, reputation, DID standards
+
+## Priority Actions (from both reports combined)
+### NOW — Ship This Week
+- [ ] Extract L402 server skeleton → integrate with token-gated-economy
+- [ ] Extract AdaptiveCalibrator → standalone cost estimation module
+- [ ] Extract SovereignRegistration → Nostr auth for the platform
+- [ ] File new Gitea issues for implementation tasks from Report #2's roadmap
+
+### NEXT — This Month  
+- [ ] Implement refund state machine (keysend-first approach)
+- [ ] WebLN integration in the-matrix frontend
+- [ ] Channel liquidity automation scripts
+
+### LATER — Architecture
+- [ ] ZK reputation proofs
+- [ ] DID document resolution
+- [ ] Decentralized dispute resolution
+- [ ] Oracle-based cost verification
+
+## Code Artifacts (extractable from Report #2)
+1. L402 FastAPI server skeleton
+2. LNDInvoiceManager class  
+3. SettlementMonitor (gRPC streams)
+4. AdaptiveCalibrator (online learning cost estimation)
+5. NostrIdentityManager (BIP44 derivation)
+6. CrossIdentityVerifier (Nostr ↔ Lightning)
+7. NostrAuthChallenge (challenge-response)
+8. SovereignRegistration (full registration flow)
+9. ZeroKnowledgeReputation (Merkle + range proofs)
+10. Sybil resistance analyzer (graph-based)
+
+## Kimi Token Budget
+- Used: 2 tokens (Report #1 + Report #2)
+- Remaining: ~97 tokens
+- Queue: 5 prompts at ~/.timmy/kimi-research-queue.md
+- Status: Batch 1 prompts (L402, Nostr, Refunds) may be REDUNDANT now
+  → Report #2 covers L402 and Nostr identity extensively
+  → Redirect Batch 1 tokens to: Lightning node operations, agent-to-agent economy, WebLN/browser integration