cross-review

# Cross-Review: Parallel Dual Review ## Overview Parallel review workflow between Claude and Codex CLI. Both models review the same artifact **simultaneously and independently**, then findings go through a three-stage resolution pipeline: initial triage → cross-validation (each model verifies the other's findings) → evidence-based research (documentation/code inspection for remaining disputes). Only genuinely inconclusive disagreements reach the user. Repeats until clean or max rounds reached. Auto-apply is the default; the user is consulted only for needs-decision items where evidence couldn't break a tie. **Core principle:** Two independent perspectives are stronger than one. Neither model sees the other's review until triage. Disagreements are resolved by **evidence first** (cross-validation, then documentation/code research) — the user is only asked to decide when evidence is genuinely inconclusive. Confirmed findings are applied automatically; the user is consulted only for genuinely inconclusive disagreements. ## Trigger Phrases "cross-review", "dual review", "multi-model review", "get a second opinion", "validate with another model", "review with codex", "parallel review" ## Invocation ``` cross-review [--max-rounds N] [--type code|plan|architecture|design] [target files...] ``` | Argument | Default | Description | |----------|---------|-------------| | `--max-rounds` | `3` | Maximum review-fix iteration rounds | | `--type` | (auto-detected) | Artifact type ove...