refactor: replace orchestrator/verifier chain with direct LiteLLM calls

Drop the three-layer Claude subprocess orchestration (local model →
Claude verifier → cloud escalation). Skills now call LiteLLM directly
and return plain text to Claude Code, which decides what to do with it.

- Delete executor, orchestrator, verifier, result, attempts packages
- Simplify LiteLLMExecutor: Run(Request)→Result becomes Complete(model,sys,user)→(string,int64,error)
- Replace ExecutorFn with CompleteFunc in all 6 skill configs
- Rewrite all skill handlers to call Complete and return {"text","model","duration_ms"}
- Simplify config/models: remove Verifier/LlamaSwapURL, add ModelFor
- Bump version to v0.5.0

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

config/models.yaml

@@ -1,41 +1,25 @@
-# Model routing chains — three-layer priority:
-# 1. model param in MCP tool call (caller override — collapses to single entry, no escalation)
-# 2. per-skill chain here
-# 3. default_chain fallback
-
-verifier: claude-sonnet-4-6   # fixed verifier for all local tiers
-
-llama_swap_url: http://koala:8080   # for warm-state probing
+# Model selection — first entry per skill is used.
+# Override per-call by passing model in the MCP tool args.
 
 default_chain:
   - ollama/qwen3-coder-30b-tuned
-  - claude-sonnet-4-6
 
 skills:
   tdd:
     chain:
       - ollama/qwen3-coder-30b-tuned
-      - claude-sonnet-4-6
   review:
     chain:
       - ollama/devstral-tuned
-      - ollama/gemma4
-      - claude-sonnet-4-6
   debug:
     chain:
       - ollama/deepseek-r1-tuned
-      - claude-sonnet-4-6
   spec:
     chain:
       - ollama/phi4
-      - ollama/gemma4
-      - claude-sonnet-4-6
-      - claude-opus-4-6
   retrospective:
     chain:
       - ollama/qwen3-coder-30b-tuned
-      - claude-sonnet-4-6
   trainer:
     chain:
       - ollama/qwen3-coder-30b-tuned
-      - claude-sonnet-4-6