fix: pass drift data via step outputs — agent can't access activation filesystem

[PureWeen]

Third iteration fixing the instruction-drift workflow.

Problem chain:

1. PR feat: gh-aw skills, security scanner, and instruction drift tooling #653: Scripts ran inside agent container → gh CLI not authenticated → scripts failed
2. PR fix: run drift check scripts in steps: where gh CLI is authenticated #662: Moved to steps: (activation job) → scripts ran with GH_TOKEN ✅ but files written to activation filesystem aren't available in agent job (different runner)
3. This PR: Pass data via $GITHUB_OUTPUT → template substitution inlines JSON directly into the agent prompt

How it works now:

activation job (steps:, has GH_TOKEN):
  ├── Check-Staleness.ps1 → $GITHUB_OUTPUT (changes_detected + report JSON)
  └── Scan-GhAwUpdates.ps1 → $GITHUB_OUTPUT (upstream JSON, only if stale)
      ↓ template substitution
agent prompt (data inlined, no file I/O):
  ├── changes_detected: false → call noop immediately
  └── changes_detected: true → analyze + create PR

The agent sees the actual JSON data right in its prompt — no cat commands, no file paths, no filesystem dependency.