feat(llm-security-copilot): port llm-security v5.1.0 to GitHub Copilot CLI

Full port of llm-security plugin for internal use on Windows with GitHub
Copilot CLI. Protocol translation layer (copilot-hook-runner.mjs)
normalizes Copilot camelCase I/O to Claude Code snake_case format — all
original hook scripts run unmodified.

- 8 hooks with protocol translation (stdin/stdout/exit code)
- 18 SKILL.md skills (Agent Skills Open Standard)
- 6 .agent.md agent definitions
- 20 scanners + 14 scanner lib modules (unchanged)
- 14 knowledge files (unchanged)
- 39 test files including copilot-port-verify.mjs (17 tests)
- Windows-ready: node:path, os.tmpdir(), process.execPath, no bash

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

plugins/llm-security-copilot/templates/archive/README.md

@@ -0,0 +1,21 @@
+# Archived Templates
+
+These templates were replaced by `templates/unified-report.md` in v1.4.0.
+
+The unified template uses conditional sections activated by `ANALYSIS_TYPE` to serve
+all 9 report formats from a single file. See the section activation table at the top
+of `unified-report.md` for the mapping.
+
+## Archived Files
+
+| File | Replaced by ANALYSIS_TYPE |
+|------|--------------------------|
+| `scan-report.md` | `scan` |
+| `deep-scan-report.md` | `deep-scan` |
+| `audit-report.md` | `audit` |
+| `posture-scorecard.md` | `posture` |
+| `plugin-audit-report.md` | `plugin-audit` |
+| `mcp-audit-report.md` | `mcp-audit` |
+| `threat-model-report.md` | `threat-model` |
+| `pre-deploy-report.md` | `pre-deploy` |
+| `clean-report.md` | `clean` |