Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
gexijin avatar

Codex Cli

  • 1 installs
  • 1 repo stars
  • Updated February 8, 2026
  • gexijin/vitiligo

Delegates coding tasks and code review to OpenAI's Codex CLI, supporting non-interactive execution, uncommitted/branch/commit reviews, and full-auto sandboxed runs.

About

Integrates OpenAI's Codex CLI to run code reviews and execute coding tasks non-interactively. A developer uses it to delegate coding work to Codex or run reviews of uncommitted changes, branches, or commits.

  • Reviews uncommitted changes, a base branch, a specific commit, or with custom instructions
  • Runs tasks via codex exec, including a sandboxed full-auto mode

Codex Cli by the numbers

  • 1 all-time installs (skills.sh)
  • Ranked #14,098 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Jul 24, 2026 (Skillselion catalog sync)
npx skills add https://github.com/gexijin/vitiligo --skill codex-cli

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1
repo stars1
Last updatedFebruary 8, 2026
Repositorygexijin/vitiligo

What it does

Delegates coding tasks and code review to OpenAI's Codex CLI, supporting non-interactive execution, uncommitted/branch/commit reviews, and full-auto sandboxed runs.

Files

SKILL.mdMarkdownGitHub ↗

OpenAI Codex CLI Skill

This skill provides integration with OpenAI's Codex CLI for code review and task execution.

Quick Reference

Code Review

Review uncommitted changes:

codex review --uncommitted

Review against a branch:

codex review --base main

Review a specific commit:

codex review --commit <sha>

Review with custom instructions:

codex review "Focus on security vulnerabilities"

Task Execution

Run a task non-interactively:

codex exec "<prompt>"

With full auto mode (sandboxed automatic execution):

codex exec --full-auto "<prompt>"

With specific model:

codex exec -m o3 "<prompt>"

Available Commands

CommandDescription
codex reviewRun code review non-interactively
codex execRun tasks non-interactively
codexInteractive mode
codex applyApply latest diff from Codex agent
codex resumeResume previous session

Review Command Options

OptionDescription
--uncommittedReview staged, unstaged, and untracked changes
--base <branch>Review changes against base branch
--commit <sha>Review changes from a specific commit
--title <title>Optional commit title for review summary
-c model=<model>Use specific model

Exec Command Options

OptionDescription
-m, --model <model>Model to use (e.g., o3, gpt-4)
-s, --sandbox <mode>Sandbox: read-only, workspace-write, danger-full-access
--full-autoLow-friction sandboxed automatic execution
-C, --cd <dir>Working directory
-i, --image <file>Attach image(s) to prompt
-o, --output-last-message <file>Write final response to file
--jsonOutput events as JSONL

Common Use Cases

1. Quick Code Review

Review current changes before committing:

codex review --uncommitted

2. PR Review

Review all changes in a feature branch:

codex review --base main --title "Feature: Add user authentication"

3. Focused Review

Review with specific focus:

codex review --uncommitted "Focus on:
1. Security vulnerabilities
2. Error handling
3. Performance issues"

4. Automated Task

Run a coding task:

codex exec "Add input validation to all API endpoints in src/api/"

5. Code Explanation

Get explanation of complex code:

codex exec "Explain the algorithm in src/utils/ranking.R"

6. Bug Investigation

Investigate test failures:

codex exec "Investigate why tests in tests/unit/ are failing"

Sandbox Modes

ModePermissions
read-onlyCan read files, no writes
workspace-writeCan write to workspace (default with --full-auto)
danger-full-accessFull system access (use with caution)

Integration with Claude Code

When using this skill:

1. For code review: Use /codex-review command or run codex review directly 2. For tasks: Use /codex command or run codex exec directly 3. For complex workflows: Combine Codex output with Claude Code analysis

Example Workflow

1. Use Codex for initial review:

   codex review --uncommitted > review.txt

2. Have Claude Code analyze and summarize:

  • Read the review output
  • Identify critical issues
  • Suggest fixes

Best Practices

1. Use `--full-auto` for routine tasks - Speeds up execution with safe defaults 2. Specify `--base` for PR reviews - Ensures complete diff is reviewed 3. Add context to review prompts - Better reviews with specific focus areas 4. Check sandbox mode - Use appropriate permissions for the task 5. Save output for complex reviews - Use -o flag for later analysis

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.