Codex Code Review Skill Trigger Conditions Triggered when user input contains: "代码审核", "代码审查", "审查代码", "审核代码" "review", "code review", "review code", "codex 审核" "帮我审核", "检查代码", "审一下", "看看代码" Core Concept: Intention vs Implementation Running codex review --uncommitted alone only shows AI "what was done (Implementation)". Recording intention first tells AI "what you wanted to do (Intention)". "Code changes + intention description" as combined input is the most effective way to improve AI code review quality. Skill Architecture This skill operates in two phases: Preparation Phase (current context): Check working directory, update CHANGELOG Review Phase (isolated context): Invoke Task tool to execute Lint + codex review (using context: fork to reduce context waste) Execution Steps 0. [First] Check Working Directory Status git diff --name-only && git status --short Decide review mode based on output: Has uncommitted changes → Continue with steps 1-4 (normal flow) Clean working directory → Directly invoke codex-runner: codex review --commit HEAD 1. [Mandatory] Check if CHANGELOG is Updated Before any review, must check if CHANGELOG.md contains description of current changes.
Check if CHANGELOG.md is in uncommitted changes
- git
- diff
- --name-only
- |
- grep
- -E
- "(CHANGELOG|changelog)"
- If CHANGELOG is not updated, you must automatically perform the following (don't ask user to do it manually):
- Analyze changes
-
- Run
- git diff --stat
- and
- git diff
- to get complete changes
- Auto-generate CHANGELOG entry
-
- Generate compliant entry based on code changes
- Write to CHANGELOG.md
-
- Use Edit tool to insert entry at top of
- [Unreleased]
- section
- Continue review flow
- Immediately proceed to next steps after CHANGELOG update Auto-generated CHANGELOG entry format:
[Unreleased]
Added / Changed / Fixed
Feature description: what problem was solved or what functionality was implemented
Affected files: main modified files/modules Example - Auto-generation Flow: 1. Detected CHANGELOG not updated 2. Run git diff --stat, found handlers/responses.go modified (+88 lines) 3. Run git diff to analyze details: added CompactHandler function 4. Auto-generate entry:
Added
- Added
/v1/responses/compactendpoint for conversation context compression - Supports multi-channel failover and request body size limits
- Use Edit tool to write to CHANGELOG.md
- Continue with lint and codex review
- [Critical] Stage All New Files Before invoking codex review, must add all new files (untracked files) to git staging area, otherwise codex will report P1 error.
Check for new files
git status --short | grep "^??" If there are new files, automatically execute:
Safely stage all new files (handles empty list and special filenames)
git ls-files --others --exclude-standard -z | while IFS = read -r -d '' f ; do git add -- " $f " ; done Explanation: -z uses null character to separate filenames, correctly handles filenames with spaces/newlines while IFS= read -r -d '' reads filenames one by one git add -- "$f" uses -- separator, correctly handles filenames starting with - When no new files exist, loop body doesn't execute, safely skipped This won't stage modified files, only handles new files codex needs files to be tracked by git for proper review 3. Evaluate Task Difficulty and Invoke codex-runner Count change scale:
Get summary line for ALL changes (staged + unstaged)
IMPORTANT: Must use 'HEAD' as base to include both staged and unstaged changes
git diff --stat HEAD | tail -1 Why use git diff --stat HEAD : git diff --stat only shows unstaged changes git diff --cached --stat only shows staged changes git diff --stat HEAD shows BOTH staged and unstaged changes combined The last line ( tail -1 ) is the summary line with total file count and line changes Difficulty Assessment Criteria: Model + Reasoning Effort Combinations: Combination Quality Time Timeout Recommended For model=gpt-5.2 model_reasoning_effort=xhigh Best ~15-20 min 40 min Critical code, architecture changes model=gpt-5.3-codex model_reasoning_effort=xhigh High ~8-9 min 15 min Difficult tasks (default) model=gpt-5.2 model_reasoning_effort=high High ~8-9 min 15 min Alternative for difficult tasks model=gpt-5.3-codex model_reasoning_effort=high Good ~5-6 min 10 min Normal tasks (default) Critical Tasks (meets any condition, use best quality model): Modified files ≥ 30 Total code changes (insertions + deletions) ≥ 2000 lines Involves core architecture/algorithm changes (user explicitly mentioned) Config: --config model=gpt-5.2 --config model_reasoning_effort=xhigh , timeout 40 minutes Difficult Tasks (meets any condition): Modified files ≥ 10 Total code changes (insertions + deletions) ≥ 500 lines Single metric: insertions ≥ 300 lines OR deletions ≥ 300 lines Cross-module refactoring Default config: --config model=gpt-5.3-codex --config model_reasoning_effort=xhigh , timeout 15 minutes Normal Tasks (other cases): Default config: --config model=gpt-5.3-codex --config model_reasoning_effort=high , timeout 10 minutes Evaluation Method: You MUST parse the git diff --stat HEAD output correctly to determine difficulty:
Get the summary line (last line of git diff --stat HEAD)
git diff --stat HEAD | tail -1
Example outputs:
"20 files changed, 342 insertions(+), 985 deletions(-)"
"1 file changed, 50 insertions(+)" # No deletions
"3 files changed, 120 deletions(-)" # No insertions
Critical: Why the summary line matters:
Each file shows individual stats:
file.go | 171 ++++++++++++++++++++-
Only the LAST line has the total:
6 files changed, 1341 insertions(+), 18 deletions(-)
You must extract the last line with
tail -1
to get accurate totals
Parsing Rules:
Extract file count from "X file(s) changed" (handle both "1 file" and "N files")
Extract insertions from "Y insertion(s)(+)" if present (handle both "1 insertion" and "N insertions"), otherwise 0
Extract deletions from "Z deletion(s)(-)" if present (handle both "1 deletion" and "N deletions"), otherwise 0
Calculate total changes = insertions + deletions
Important Edge Cases:
Single file:
"1 file changed"
(singular form)
No insertions: Git omits
"insertions(+)"
entirely → treat as 0
No deletions: Git omits
"deletions(-)"
entirely → treat as 0
Pure rename: May show
"0 insertions(+), 0 deletions(-)"
or omit both
Decision Logic (check in order, first match wins):
IF file_count >= 30 OR total_changes >= 2000 →
Critical
(gpt-5.2 + xhigh)
IF file_count >= 10 →
Difficult
(gpt-5.3-codex + xhigh)
IF total_changes >= 500 →
Difficult
(gpt-5.3-codex + xhigh)
IF insertions >= 300 OR deletions >= 300 →
Difficult
(gpt-5.3-codex + xhigh)
ELSE →
Normal
(gpt-5.3-codex + high)
Example Cases:
⭐ "50 files changed, 2000 insertions(+), 1500 deletions(-)" →
关键任务
，使用
model=gpt-5.2 model_reasoning_effort=xhigh
，超时 40 分钟（核心架构变更）
✅ "20 files changed, 342 insertions(+), 985 deletions(-)" →
困难任务
，使用
model=gpt-5.3-codex model_reasoning_effort=xhigh
，超时 15 分钟
✅ "5 files changed, 600 insertions(+), 50 deletions(-)" →
困难任务
，使用
model=gpt-5.3-codex model_reasoning_effort=xhigh
，超时 15 分钟
❌ "3 files changed, 150 insertions(+), 80 deletions(-)" →
普通任务
，使用
model=gpt-5.3-codex model_reasoning_effort=high
，超时 10 分钟
❌ "1 file changed, 50 insertions(+)" →
普通任务
，使用
model=gpt-5.3-codex model_reasoning_effort=high
，超时 10 分钟
Invoke codex-runner Subtask:
Use Task tool to invoke codex-runner, passing complete command (including Lint + codex review):
Task parameters:
- subagent_type: Bash
- description: "Execute Lint and codex review"
- timeout: 900000 (15 minutes for difficult tasks) or 600000 (10 minutes for normal tasks)
- prompt: Choose corresponding command based on project type and difficulty
Go project - Difficult task:
go fmt ./... && go vet ./... && codex review --uncommitted --config model=gpt-5.3-codex --config model_reasoning_effort=xhigh
(timeout: 900000)
Go project - Normal task:
go fmt ./... && go vet ./... && codex review --uncommitted --config model=gpt-5.3-codex --config model_reasoning_effort=high
(timeout: 600000)
Node project - Difficult task:
npm run lint:fix && codex review --uncommitted --config model=gpt-5.3-codex --config model_reasoning_effort=xhigh
(timeout: 900000)
Node project - Normal task:
npm run lint:fix && codex review --uncommitted --config model=gpt-5.3-codex --config model_reasoning_effort=high
(timeout: 600000)
Python project - Difficult task:
black . && ruff check --fix . && codex review --uncommitted --config model=gpt-5.3-codex --config model_reasoning_effort=xhigh
(timeout: 900000)
Python project - Normal task:
black . && ruff check --fix . && codex review --uncommitted --config model=gpt-5.3-codex --config model_reasoning_effort=high
(timeout: 600000)
Clean working directory:
codex review --commit HEAD --config model=gpt-5.3-codex --config model_reasoning_effort=high
(timeout: 600000)
4. Self-Correction
If Codex finds Changelog description inconsistent with code logic:
Code error
→ Fix code
Description inaccurate
→ Update Changelog
Complete Review Protocol
[GATE] Check CHANGELOG
- Auto-generate and write if not updated (leverage current context to understand change intention)
[PREPARE] Stage Untracked Files
- Add all new files to git staging area (avoid codex P1 error)
[EXEC] Task → Lint + codex review
- Invoke Task tool to execute Lint and codex (isolated context, reduce waste)
[FIX] Self-Correction
- Fix code or update description when intention ≠ implementation
Codex Review Command Reference
Basic Syntax
codex review
[
OPTIONS
]
[
PROMPT
]
Note
:
[PROMPT]
parameter cannot be used with
--uncommitted
,
--base
, or
--commit
.
Common Options
Option
Description
Example
--uncommitted
Review all uncommitted changes in working directory (staged + unstaged + untracked)
codex review --uncommitted
--base