Codex review

Skill Studio-Moser/skills-n-stuff/plugins/pm/skills/codex-review

Product research, market intelligence, and content tools for AI-native teams

Install

npx -y skills add Studio-Moser/skills-n-stuff --skill codex-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Ask the Codex CLI (running whatever model it's configured with) for an independent code review of uncommitted changes, a branch diff, a commit, or a specific implementation. This is how the Codex model is invoked for review work. Use when the user asks Claude to have Codex review work, when the model-selection rubric calls for a cross-vendor review perspective, or when Codex should audit a diff, find bugs or regressions, or compare Claude's implementation against requirements. For a review by Claude itself, use the normal review process instead.

SKILL.md

3.0 KB, as published. Nobody here has run it

Codex Review

Optional cross-vendor executor. Requires the OpenAI codex CLI. If command -v codex fails, this skill isn't available on this machine — say so and fall back to a native review. The model-orchestration doctrine (references/model-orchestration.md) routes here only when the CLI is present.

Use Codex as an independent reviewer when the user wants a second-pass review or when a change is broad enough that another agent's perspective is useful.

Prefer Claude's normal review process for small local checks. Do not delegate review just to avoid reading the code yourself. Treat Codex's output as evidence, not authority.

Workflow

Identify the review target: uncommitted changes, base branch, commit SHA, PR checkout, or specific files.
Create a temporary artifact directory for the Codex report.
Run codex review with a focused review prompt.
Read Codex's report and verify important claims against the code before presenting them.

Use one of these command shapes:

ARTIFACT_DIR="$(mktemp -d "${TMPDIR:-/tmp}/codex-review.XXXXXX")"
REPORT="$ARTIFACT_DIR/report.md"
PROMPT="$ARTIFACT_DIR/prompt.md"

# Review staged, unstaged, and untracked changes.
codex -C "$PWD" review --uncommitted - < "$PROMPT" > "$REPORT"

# Review current branch against a base branch.
codex -C "$PWD" review --base main - < "$PROMPT" > "$REPORT"

# Review a single commit.
codex -C "$PWD" review --commit <sha> - < "$PROMPT" > "$REPORT"

Review Prompt

Ask Codex to use a code-review stance:

Review these changes for bugs, regressions, missing tests, security issues, and requirement mismatches.

Prioritize findings over summary. For each finding include:
- severity
- file and line reference
- concrete failure mode
- suggested fix direction

Do not edit files. If there are no substantive findings, say so and name any residual test gaps.

Add task-specific context when useful: requirements, risky areas, expected behavior, relevant tests, or files Claude is unsure about.

Reporting Back

Before relaying a Codex finding, inspect the cited code or diff enough to decide whether the finding is real. In the user-facing response, separate confirmed issues from Codex suggestions you did not verify.

If Codex finds nothing, say that clearly and mention what review target it inspected.

If codex is not installed or the command fails, report the error and offer to review the changes directly instead.