Self-run
SKILL
Codex Review Full
Use when Claude has written a plan and the user wants codex to verify it against the actual codebase — runs gpt-5.5 and gpt-5.4 at xhigh reasoning in parallel with full shell access, iterates until both converge. Strict prompt-level prohibition on destructive operations. Prefer `/codex-review` for fast, deterministic reviews that don't need ground-truth checks.
0
22
Free Self-run
SKILL
Codex Review
Use when Claude has written a plan and the user wants codex to premortem it — by default runs gpt-5.5 and gpt-5.4 at xhigh reasoning in parallel, iterates until both converge. Also supports single-shot codex runs, resume, and edit/network sandboxes as escape hatches.
0
26
Free You've reached the end · 2 loaded