code-review README documents a git blame agent and 0-100 confidence scoring that no longer exist in the command

plugins/code-review/README.md describes a review pipeline that no longer matches commands/code-review.md:

• "Agent #4: Analyze git blame/history for context-based issues" (line 22): the command has no blame or history agent; agents 3 and 4 are both bug-scan agents focused on the diff.
• A 0-100 confidence scoring system with an 80 threshold (lines 3, 7, 23-24, 45-46, 52, 78-83, 101, 165, 179, 207, 210, 239-243): the command uses per-issue validation subagents (steps 5-6) with no numeric scoring anywhere.
• The Configuration section (lines 214-221) tells users to edit the line "Filter out any issues with a score less than 80." in commands/code-review.md. That line does not exist in the file, so the documented customization is a dead end.

Verified with grep: the command file has zero occurrences of scoring, thresholds, or git blame; the README has 17 mentions across those features. Happy to open a PR aligning the README with the current validation-based flow.