Menu
Codex code review closeout: local dirty changes, PR branch vs main, parallel tests.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Build and deploy sites and Spot Show card/block visual reports on Spot, the internal hosting platform. Use when creating or updating a Spot site, showing plans, architecture diagrams, diffs, terminal output, JSON, screenshots, or when a site needs identity, database, realtime, file uploads, text AI, AI image generation, or Slack notifications.
Manage git worktrees with the gt utility for parallel feature development — create, switch, merge, and clean up worktrees without stashing or branch-switching.
Use before any creative work or significant changes. Activates on "brainstorm", "let's brainstorm", "deep analysis", "analyze this feature", "think through", "help me design", "explore options for", or when user asks for thorough analysis of changes, features, or architectural decisions. Guides collaborative dialogue to turn ideas into designs through one-at-a-time questions, approach exploration, and incremental validation.
Prove and counter-prove a statement using parallel agents to eliminate confirmation bias. Use when someone says "dialectic", "prove/disprove", "stress test this claim", "is this really true", "argue both sides", or when a statement needs objective analysis from opposing viewpoints.
Run an LLM code review (OpenAI Codex + Anthropic Claude in parallel) on uncommitted changes or against a base ref. Use when user asks to "review my changes", "review uncommitted", "review against <ref>", "code review", "LLM review", "review branch vs <ref>", "second opinion on this diff".
Use after a fix or PR branch is already implemented when the user asks Codex to independently reproduce the original issue on a pre-fix baseline, apply the current branch's fix, reload/reset local data if needed, verify the actual corrected behavior through both data-level checks and realistic browser/UI flows when user-visible behavior is involved, investigate any remaining failures, and report evidence back without changing product code. Triggers include "reproduce then test the fix", "verify this branch locally", "prove the issue is gone", "use local dev env", "test API and browser", "make screenshots", "human test this", or "generate a report".
| name | codex-review |
| description | Codex code review closeout: local dirty changes, PR branch vs main, parallel tests. |
Run Codex's built-in code review as a closeout check. This is code review (codex review), not Guardian auto_review approval routing.
Use when:
--full-access option instead of changing models.codex review just to get a nicer "clean" line, a second opinion, or clearer closeout wording.Dirty local work:
codex review --uncommitted
Use this only when the patch is actually unstaged/staged/untracked in the
current checkout. For committed, pushed, or PR work, review the branch against
its base instead; do not force --mode local / --uncommitted just because the
helper docs mention dirty work first. A clean --uncommitted review only proves
there is no local patch.
Branch/PR work:
git fetch origin
codex review --base origin/main
Do not pass an inline prompt with --base; current CLI rejects --base + [PROMPT] even though help text is ambiguous. If custom instructions are needed, run the plain base review first, then do a local/manual follow-up pass.
If an open PR exists, use its actual base:
base=$(gh pr view --json baseRefName --jq .baseRefName)
codex review --base "origin/$base"
Committed single change:
codex review --commit HEAD
Format first if formatting can change line locations. Then it is OK to run tests and review in parallel:
scripts/codex-review --parallel-tests "<focused test command>"
Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review until no accepted/actionable findings remain. Once that rerun exits cleanly, stop; do not spend another long review cycle on redundant confirmation.
Codex review is usually noisy. Default to a subagent filter when subagents are available. Ask it to run the review and return only:
Run inline only for tiny changes or when subagents are unavailable.
Bundled helper:
~/.codex/skills/codex-review/scripts/codex-review --help
If installed from agent-scripts, path is:
/Users/steipete/Projects/agent-scripts/skills/codex-review/scripts/codex-review --help
The helper:
--uncommitted firstgh pr view worksorigin/main for non-main branches--mode auto or forced to --mode branch for committed/PR work; do not force --mode local after committing--output or CODEX_REVIEW_OUTPUT is set--dry-run and --parallel-tests--full-access for nested review runs that need localhost bind/listen testscodex-review clean: no accepted/actionable findings reported when the selected review command exits 0Include:
Do not run another Codex review solely to improve the final report wording. If the final helper run exited 0 and produced no accepted/actionable findings, report that exact run as clean.