Local Codex Review (pre-push)

Runs the exact same review Codex performs in CI (.github/workflows/codex-pr-review.yml), but locally and scoped to work you have not pushed yet, so you catch what CI would flag before the PR exists. Use this before git push on a non-trivial change.

Correspondence with CI, identical:

• Policy: REVIEW.md (severity triage, public-surface checklist, AGENTS.md compliance, test coverage).
• Model: gpt-6.1-sol.
• Reasoning effort: model_reasoning_effort="xhigh".
• Output: markdown starting with ## Codex Review, findings tagged P0 / P1 / P2 with file:line.

Differences from CI, local-only:

• Scope is the current branch vs main at the merge-base, including uncommitted changes (CI reviews a pushed PR diff).
• Sandbox is read-only (CI uses danger-full-access on an ephemeral runner). Codex reads the diff and files but cannot modify your working tree.
• Fresh context is inherent: codex exec is a separate cold process, so it does not anchor on the current chat session, the same reason local-review insists on a subagent.

Prerequisites

• codex CLI >= 0.159.3 installed and authed via codex login or an OPENAI_API_KEY in the environment (which takes priority). Older CLIs reject the model with "requires a newer version of Codex"; run.sh checks the version up front. Upgrade with npm install --global @openai/codex@0.159.3 (may need sudo for a global install). This matches the pin in .github/workflows/codex-pr-review.yml, the CLI version is the same on both sides.
• git fetch the base ref if it's stale, so the merge-base is accurate.

Run

bash .agents/skills/local-review-codex/run.sh          # review vs main (default)
bash .agents/skills/local-review-codex/run.sh <base>   # review vs a different base ref