chore(agents): sync agent configs, models, capability index; cleanup junk

- Update agent model assignments (minimax/glm -> nemotron-3-ultra, kimi-k2.7-code, qwen3.5:397b) in .kilo/agents, kilo-meta.json, kilo.jsonc, capability-index.yaml
- Update orchestrator/agent prompts (complexity fast-path, verification tests, close-loop audit)
- Add .kilo/KILO_SPEC.md (Kilo Code specification reference)
- AGENTS.md: consolidate smartadmin agent rows
- Remove screenshot-dash.cjs (unused, contained hardcoded admin token); gitignore it
- Remove empty .kilo/milestones/

.kilo/agents/reflector.md

@@ -1,10 +1,12 @@
 ---
 description: Self-reflection agent using Reflexion pattern - learns from mistakes
 mode: subagent
-model: ollama-cloud/glm-5.2
+model: ollama-cloud/minimax-m3
 variant: thinking
 color: "#10B981"
 permission:
+  bash: ask
+  write: ask
   edit: allow
   read: allow
   grep: allow
@@ -63,3 +65,13 @@ After completion, recommend next agent in event footer:
 - `code-skeptic`: after code written
 - `performance-engineer`: after code tested
 - `security-auditor`: after performance reviewed
+
+## Episodic Learning
+
+At pipeline end, the reflector reads the last N entries (default 20) from `.kilo/logs/agent-executions.jsonl` and `.kilo/logs/episodic-lessons.jsonl` (if present), extracts success/failure patterns, and appends new lessons to `episodic-lessons.jsonl`.
+
+```jsonl
+{"ts":"ISO","lesson":"pattern description","from_agent":"agent-name","issue":N,"applied_to":["agent1","agent2"],"success":true}
+```
+
+Lessons are tagged with `applied_to` listing agent names that should integrate them. The prompt-optimizer reads these lessons when improving prompts.