refactor(health-plugin): extract health-plugins inline commands to standalone scripts

[laurigates]

Problem

The health-plugins skill uses 4 shell utility Bash patterns (test, jq, cp, mkdir) in its allowed-tools frontmatter. This forces Claude to generate inline bash commands that each require individual user approval, since complex/compound commands can't be allowlisted via Bash(command *) patterns.

Current allowed-tools:

allowed-tools: Bash(test *), Bash(jq *), Bash(cp *), Bash(mkdir *), Read, Write, Edit, Glob, Grep, TodoWrite, AskUserQuestion

Expected behavior

Consolidate shell utility operations into standalone scripts in health-plugin/skills/health-plugins/scripts/ and use Bash(bash *) permission pattern, following the pattern established in health-plugin/skills/health-check/scripts/.

Reference

• See health-plugin/skills/health-check/ for the correct pattern (refactored in this PR)
• Rule: .claude/rules/agentic-permissions.md → "Scripts for Compound Operations"
• Detected by: scripts/plugin-compliance-check.sh Check 6 (check_bash_patterns)

Affected skills

Skill	Shell utility patterns
health-plugins	test, jq, cp, mkdir (4 patterns)