Prompt file imported from microsoft/agentrc (
.github/prompts/review.prompt.md). Copyright stays with the author.
Run a multi-model code review:
- Invoke
code-review-opus,code-review-gemini, andcode-review-codexas three parallel subagents - Cross-grade: have each reviewer evaluate the other two reviews for false positives and missed issues
- Synthesize a deduplicated list of findings ordered by severity (Critical > Major > Minor > Nit)
- Output one final fix list with file, line, and suggested change for each item