Add LLM key-hunter toolkit, vault, and skill

- tools/scripts/llm-key-hunter: GitHub leak hunting pipeline (hunt_*,
  pivot miner, two-layer verify/content caches, per-provider verification)
- usable_keys: verified key vault across 12 providers (deepseek, minimax,
  volcanoark, longcat, codingplan, zhipu free-tier, mimo, siliconflow, etc.)
- .grok/skills/llm-key-hunter: operator skill for the hunt/verify/vault flow
- NewAPI channel import scripts and CDP capture helpers
- Result verdict buckets (excluding multi-GB blob caches and dedup dumps)

tools/scripts/llm-key-hunter/usable_keys/minimax/key_01_sk-cp-78BJu2Lhi7FGVnV1.txt

@@ -0,0 +1,7 @@
+PROVIDER : minimax - MiniMax Coding Plan
+KEY      : sk-cp-78BJu2Lhi7FGVnV1xvzDnj0J3b9AdDojkIQMAuDc03OSn5gI3pHTlxntB1inbwU4M0lCtAoSbc8vxbjoJjlKyg3dQDg7ZdAQXWrZtMMZcA0wWxZYe23-fv0
+DETAIL   : https://api.minimaxi.com/v1 chat OK: '<think>\nThe user has simply sa'
+SOURCE   : https://github.com/brianleixia/chi2026-norm-emergence/blob/5dfed5b80da22579dd4e1985c9c9ba0d998bd2fa/paper/auto_research_loop.py
+BASE_URL : https://api.minimaxi.com/v1
+MODELS   : ['MiniMax-M2.5', 'MiniMax-M2.5-highspeed', 'abab6.5s-chat']
+VERIFIED : 2026-08-01 13:19 UTC