| name | cross-review |
| description | Run a cross-model code review using both opus and sonnet in parallel, then merge and deduplicate findings into a combined summary. Use when the user says cross review, dual review, cross-model review, review with both models, or wants a thorough second-opinion review of changes. |
Context
- Current branch: !
git branch --show-current
- Staged changes: !
git diff --cached --stat
- Unstaged changes: !
git diff --stat
- Recent commits: !
git log --oneline -5
Your Task
Run a cross-model code review using both opus and sonnet to catch blind spots.
Target: $ARGUMENTS
If no target specified, review all staged and unstaged changes. If no changes exist, review the most recent commit.
Step 1: Identify What to Review
Determine the review scope:
- If a file or directory is specified → review that
- If there are staged/unstaged changes → review those
- If no changes → review the diff of the last commit (
git diff HEAD~1)
Collect the full list of files and changes to review.
Step 2: Launch Parallel Reviews
Use the Agent tool to launch TWO review agents in parallel (both in the same message):
Agent A (opus): Launch a general-purpose agent with model: opus. Provide it the list of files/changes and instruct it to review for:
- Clean code principles (naming, function size, duplication, abstraction)
- Error handling and edge cases
- Security vulnerabilities (injection, auth, data exposure)
- Pattern consistency with the existing codebase
- Performance concerns
- Test coverage gaps
It must produce a structured list of issues with severity, file path, line number, and description.
Agent B (sonnet): Launch a general-purpose agent with model: sonnet. Same files, same review criteria, independent review. This provides a second perspective.
Step 3: Merge Results
After both agents complete:
- Combine all issues from both reviews into one list
- Deduplicate — match issues that describe the same problem in the same location
- Flag consensus — issues found by BOTH models are high confidence
- Flag unique — issues found by only ONE model are worth reviewing but lower confidence
Step 4: Produce the Cross-Validation Summary
## Cross-Review Summary
**Scope:** [what was reviewed]
**Models:** opus + sonnet
### Must Fix (found by both models)
- [Issue] — `file:line` — [description]
### Should Fix (found by one model)
- [Issue] — `file:line` — [found by: opus|sonnet] — [description]
### Consider
- [Suggestion] — `file:line` — [found by: opus|sonnet] — [description]
### What Looks Good
- [Positive observations agreed on by both models]
### Stats
- Total issues: X (Y must fix, Z should fix, W consider)
- Consensus issues (both models): X
- Opus-only issues: X
- Sonnet-only issues: X
### Next Step
Run `/fix-issues` to address all must-fix and should-fix items.
IMPORTANT: Do NOT ask the user whether to run either review. Both models run automatically. This is the entire purpose of this skill.
