codex-pr-review

A command that asks OpenAI Codex to review the current code branch against a base branch and return structured findings. A branch is a separate line of code changes, and the base branch is the version used for comparison.

In plain words
What is it for?
Use it to detect the project environment, choose a comparison branch, verify that the Codex command-line tool is installed, and run a standalone pull-request review.
Why use it?
It gives developers a repeatable way to inspect their changes before merging them.

Command

Part of the pr-review-fix-loop plugin — 1 skill, 2 commands, 2 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/dapi/claude-code-marketplace/codex-pr-review
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace

Or install pr-review-fix-loop, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 hooks.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00616
Opus 5 $0.00011 $0.00308
Sonnet 5 $0.00004 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured 3d ago against content hash 383b945ac2bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

pr-review-fix-loop/commands/codex-pr-review.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex PR Review

Запустить code review текущей ветки относительно base branch через встроенную подкоманду codex review.

Парсинг аргументов

Разобрать $ARGUMENTS:

  • --base BRANCH — base branch для сравнения (по умолчанию: автодетект или master)

Детект проекта

Получить env wrapper:

PROJECT_JSON=$("${CLAUDE_PLUGIN_ROOT}/scripts/detect-project.sh")
if [[ $? -ne 0 ]] || [[ -z "$PROJECT_JSON" ]]; then
  echo "Error: Failed to detect project" >&2
  # stop execution
fi
ENV_EXEC=$(echo "$PROJECT_JSON" | jq -r '.env_exec // empty')

Если PROJECT_JSON пуст или скрипт вернул ненулевой exit code — вывести ошибку и прекратить выполнение. Если ENV_EXEC пуст (jq вернул empty) — продолжить без env wrapper.

Определение base branch

Запустить detect-base-branch.sh с env wrapper:

BASE=$("${CLAUDE_PLUGIN_ROOT}/scripts/detect-base-branch.sh" --base "${user_base:-}" ${ENV_EXEC:+--env-exec "$ENV_EXEC"})
# NOTE: quote $BASE in all subsequent commands to handle branch names safely

Если скрипт вернул ошибку — вывести сообщение об ошибке и прекратить выполнение.

Проверки перед запуском

Убедиться что codex CLI установлен:

${ENV_EXEC:+$ENV_EXEC }which codex

Если не установлен — сообщить пользователю и прекратить выполнение.

Убедиться что есть изменения:

${ENV_EXEC:+$ENV_EXEC }git diff "$BASE"...HEAD --stat

Если diff пустой — сообщить что нет изменений для ревью и прекратить.

Запуск Codex

Использовать встроенную подкоманду codex review:

${ENV_EXEC:+$ENV_EXEC }codex review --base "$BASE"

Важно: Подкоманда review и свободный промпт взаимоисключающие — нельзя передать и --base, и текст промпта одновременно. Codex сам получит diff, проанализирует изменения и выведет структурированный отчёт.

После завершения

  1. Вывести результат ревью пользователю
  2. Если codex завершился с ошибкой — сообщить об ошибке, показать stderr

Примеры использования

/codex-pr-review
/codex-pr-review --base develop
/codex-pr-review --base HEAD~3

Read the full file on GitHub · 79 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 79 lines · 22 tokens per session scan A 383b945ac2bd

Subscribe to this mod's changes

codex-pr-review is a command published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 616 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.