docs: redesign banner — Claude AI hub + capability constellation

Old banner showed only "2 skills" which undersold the actual capability
breadth (90+ modules across 84 sections). New banner conveys the
integration story:

- 1280×680 canvas (was 1280×480) — more room for the constellation
- Top band: small accent burst + claude-osint wordmark + tagline
  "Claude in god mode" + meta block (version/MIT/author/repo URL)
- Middle band: Claude AI hub (red gradient + 8-spoke white asterisk)
  at center, 8 capability nodes orbiting at radius 200, dashed red
  connecting lines + subtle orbit rings:
    M365 / Entra · AWS · GitHub · GraphQL · Kubernetes ·
    Citrix/F5/Fortinet · Anthropic/OpenAI · HudsonRock/Wayback
  Each node shows category + concrete sub-capability detail
- Secondary capability badges in margins (Slack/Discord, Postman,
  Atlassian/DataDog, LinkedIn enum, job posting analysis, sat imagery)
- Bottom band: stat ribbon highlighting the real numbers:
    90+ MODULES · 48 SECRET PATTERNS · 80+ DORKS · 9 VALIDATORS ·
    27 ATTACK PATHS · 5,500+ LINES
- Footer: methodology + arsenal · paired · production-ready

README tagline now leads with module count (90+) instead of skill
count (2), since 2 didn't represent the capability breadth.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: elementalsouls

README.md

@@ -2,7 +2,7 @@
 
 # claude-osint
 
-> 2 production-ready offensive OSINT skills for Claude — drop-in `SKILL.md` files that turn Claude into a context-aware external recon operator for authorized red-team and bug-bounty engagements.
+> 2 paired Claude skills · **90+ recon modules** · 48 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · 5,500+ lines of structured tradecraft. Drop-in `SKILL.md` files that turn Claude into a god-mode external recon operator for authorized red-team and bug-bounty engagements.
 
 Built by **[ElementalSoul](https://github.com/elementalsouls)** — extracted from the operational tradecraft of the [Falcon-Recon](https://github.com/elementalsouls/falcon-recon) external attack-surface management platform.