cross-model-review
Cross-Model Code Review
Cross-model validation: the authoring model writes code, a different model reviews it. Different architectures, different training distributions, no self-approval bias.
Core insight: Single-model self-review is systematically biased. The same blind spots that let bugs through during writing let them through during review. Cross-model review catches different bug classes because the reviewer has fundamentally different failure modes.
How to read this skill: patterns and decision trees below are guidelines. Pick what fits, blend when needed. The rules marked ⚠️ are different: they're real CLI behaviors (yield_time_ms, the -- separator, scope flags), not procedural ceremony. A Jun 2026 audit across 4k+ Claude/Codex JSONL conversations found claude -p failures clustering around these mechanics, plus zsh wrapper mistakes. Treat them as facts about the tool, not opinions about workflow.
Direction & Pre-Flight
Identify the host first. The host runs the other model's CLI as a subprocess.
| Current host | You invoke | Direction |
|---|---|---|
| Claude Code | codex CLI |
Claude writes → Codex reviews |
| Codex | claude CLI |
Codex writes → Claude reviews |
| Pi (pi-nova pack) | /xreview (wraps codex exec) |
Pi writes → Codex reviews |
Confirm the reviewer is reachable before the real call: