docs: add workflow_run trigger examples for DevOps monitoring workflows

[Copilot]

workflow_run was mentioned 4 times in create-agentic-workflow.md with no complete examples, leaving DevOps monitoring scenarios (CI/CD failure detection, deployment alerting) poorly served.

Changes

• New section: "Creating Monitoring Workflows" — added after "Creating Command Workflows" to sit alongside other trigger pattern docs
  • deployment_status vs workflow_run distinction callout
  • Context variables reference table (conclusion, id, html_url, head_branch, head_commit.message)
  • Example 1 — minimal workflow_run + if: conclusion == 'failure' that posts a PR comment; no pre-steps
  • Example 2 — full DevOps pattern: monitors multiple workflows, pre-fetches --log-failed logs, uses cache-memory for run deduplication, and instructs the agent to post a root-cause comment
  • When-to-use checklist and agent guidance for routing monitoring requests to this pattern

Example 2 frontmatter shape:

on:
  workflow_run:
    workflows: ["CI", "Deploy"]
    types: [completed]
if: ${{ github.event.workflow_run.conclusion == 'failure' }}
permissions:
  contents: read
  actions: read        # required to download workflow run logs
tools:
  github:
    toolsets: [default]
  cache-memory: true   # deduplication: skip already-diagnosed run IDs
steps:
  - name: Fetch failed run logs
    env:
      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
      RUN_ID: ${{ github.event.workflow_run.id }}
    run: |
      gh run view "$RUN_ID" --log-failed > /tmp/gh-aw/agent/ci-logs.txt 2>&1 || true
      tail -500 /tmp/gh-aw/agent/ci-logs.txt > /tmp/gh-aw/agent/ci-logs-trimmed.txt
safe-outputs:
  add-comment:
    max: 1