docs: capture example 07 measure output and cost

[queso]

Example 07 shipped in #45 with its measure output marked "not measured". This PR replaces that with a real run: ./promptdiff measure --scenario ./examples/07-grader-file/scenario.json, 8 haiku runs through claude-p.

promptdiff measure: day-planner (haiku via claude-p)

no-overlaps
  4/4 pass (100%) | $0.1570

lunch-stays-free
  4/4 pass (100%) | $0.1351

total cost: $0.2921

The run took 97s. All 8 runs wrote schedule.json, so the README says no no-artifact count appears in this capture and shows what the line looks like when one does. The cost label in examples/README.md is updated to match.

🤖 Generated with Claude Code

[github-actions]

Nitpick review — approve

Documentation-only change adding example content to two README files, with no source, config, or test paths touched. No runtime behavior is affected and no issues were identified. Approving.

0 inline comment(s).

Verdict was approve, posted as a comment — this repo does not allow GitHub Actions to approve PRs.