/codex-review — Independent GPT Code Review

/codex-review — Independent GPT Code Review

Usage

/codex-review — reviews staged changes (git diff --staged) /codex-review HEAD~N — reviews last N commits /codex-review [file ...] — reviews specific files

Description

Get an independent GPT code review via Codex CLI. Claude evaluates each GPT finding (agree, correct, or dismiss), adds severity levels, and presents a structured actionable review.

Instructions

Phase 0: Determine Scope

• No args: run git diff --staged. If nothing staged, run git diff HEAD~1 for the last commit.
• HEAD~N pattern: run git diff HEAD~N
• File args: read the specified files directly
• If nothing found: ask the user what to review

Phase 1: Get Context (if tessera available)

1. graph_continue (mandatory first call)
2. graph_impact(changed_files=[...list of modified files...])
   → shows which parts of the codebase depend on what's being changed
3. graph_read each modified file
   → gives Claude full current file content before sending anything to GPT
4. graph_action_summary
   → surfaces locked architectural decisions; flag if review would violate any

Phase 2: Send to GPT

For diffs up to ~200 lines, send in one call. For larger diffs, send one file at a time.

codex exec "Independent code review. Context: <TASK_OR_DESCRIPTION>. Code/diff to review: <CODE_OR_DIFF>. Review for: (1) bugs and logic errors, (2) security vulnerabilities (injection, auth bypass, data exposure), (3) performance issues, (4) missing error handling, (5) readability and naming. Format each finding as: [BUG|SECURITY|PERF|STYLE|MISSING]: file:line — issue — suggested fix. End with VERDICT: approved | approved-with-notes | needs_revision"

Phase 3: Claude Evaluates

For each GPT finding, Claude:

• Confirms the finding is real (not a false positive)
• Assigns severity: CRITICAL / HIGH / MED / LOW
• Notes if the issue is already handled elsewhere in the codebase
• Adds any findings GPT missed

Phase 4: Present Review

Verdict: approved | approved-with-notes | needs_revision

CRITICAL / HIGH — Must Fix: [list with file:line and fix]

MED — Should Fix: [list]

LOW / Style — Consider: [list]

Blast Radius: [if tessera active — what this change affects downstream]

Decision Conflicts: [if any locked decisions conflict with this change — flag before proceeding]

Ask: fix critical/high issues now?

If reviewing staged changes before a commit and tessera MCP is active: run tessera-verify as a final gate to confirm all plan checklist items are satisfied.