From codex-plugin
Executes OpenAI Codex CLI commands for code analysis, review, and validation. Configures models (gpt-5.3-codex/gpt-5.2), sandbox modes (read-only/workspace-write), reasoning effort (low/medium/high/xhigh), and session resuming in terminals, Claude Code, or CI.
How this skill is triggered — by the user, by Claude, or both
Slash command
/codex-plugin:codex-cliThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
| Environment | Git Repo | Command Format |
| Environment | Git Repo | Command Format |
|---|---|---|
| Interactive terminal | Any | codex "prompt" |
| Claude Code / CI | ✅ Yes | codex exec -s read-only "prompt" |
| Claude Code / CI | ❌ No | codex exec --skip-git-repo-check -s read-only "prompt" |
Non-TTY environments (Claude Code, CI pipelines, scripts) require codex exec.
Before executing Codex commands, check if the working directory is a Git repository:
# Check Git repository status
git rev-parse --git-dir 2>/dev/null && echo "Git repo: YES" || echo "Git repo: NO"
--skip-git-repo-check flag (requires user awareness of security implications)# Basic code review (terminal)
codex "Review this code for bugs"
# Non-interactive mode (Claude Code/CI)
codex exec -s read-only "Review this code for bugs"
# With specific model and reasoning effort
codex exec -s read-only -m gpt-5.3-codex -c model_reasoning_effort=high "Deep analysis"
# With image input
codex exec -s read-only -i screenshot.png "What's shown here?"
# IMPORTANT: --skip-git-repo-check required for non-Git directories
# Ask user permission before using this flag
codex exec --skip-git-repo-check -s read-only "Review this code for bugs"
# With options
codex exec --skip-git-repo-check -s read-only -m gpt-5.3-codex "Deep analysis"
# IMPORTANT: Options must come BEFORE 'resume' subcommand
# SESSION_ID is from previous command output (e.g., 019ae3a3-f1cf-7dc1-8eee-8f424ae7a6f0)
# In Git repository
codex exec -s read-only resume [SESSION_ID] "Continue the analysis"
# Outside Git repository
codex exec --skip-git-repo-check -s read-only resume [SESSION_ID] "Continue the analysis"
codex, resume, apply, input/output patternsFull model details: See Options Reference
Note: Model names change frequently as OpenAI releases new versions. Run
codex --helpor check OpenAI Codex Models for the current list.
| Model | Best For |
|---|---|
gpt-5.3-codex | Most capable agentic coding model (recommended) |
gpt-5.2 | General AI tasks, multi-domain |
gpt-5.1-codex-max | Long-horizon agentic coding, security audits |
gpt-5-codex-mini | Quick checks, batch operations (cost-effective) |
Usage examples: See Options Reference
| Level | Use Case |
|---|---|
low | Simple checks, syntax review |
medium | Standard code review (default) |
high | Security audits, complex logic |
xhigh | Critical systems, exhaustive analysis |
| Mode | Description |
|---|---|
read-only | Cannot modify files (safest, recommended) |
workspace-write | Can modify workspace files |
danger-full-access | Full system access (use sparingly) |
Full options list: See Options Reference
Full examples: See Examples for detailed patterns
# Code review (Claude Code/CI)
codex exec -s read-only "Review: $(cat src/auth.js)"
# Maximum depth analysis
codex exec -m gpt-5.3-codex -c model_reasoning_effort=xhigh -s read-only "Security audit"
# Session continuity
codex exec -s read-only resume [SESSION_ID] "Continue analysis"
# Cross-directory
codex exec -C ./backend --add-dir ./frontend -s read-only "Review API"
# Non-Git directory (ask user first)
codex exec --skip-git-repo-check -s read-only "Analyze code"
| Issue | Description | Workaround |
|---|---|---|
-C with absolute paths | cwd is not absolute error with Windows paths like C:\path | Use relative paths (./subdir) or run from target directory |
| Path separators | Backslashes may cause issues | Use forward slashes (/) in paths |
# AVOID on Windows:
codex exec -C C:\Projects\myapp -s read-only "analyze"
# USE instead:
cd C:\Projects\myapp && codex exec -s read-only "analyze"
# OR use relative paths:
codex exec -C ./myapp -s read-only "analyze"
Error recovery patterns: See Examples
| Error | Cause | Solution |
|---|---|---|
stdin is not a terminal | Using codex in non-TTY | Use codex exec |
Not inside a trusted directory | Not in Git repo | Ask user, then use --skip-git-repo-check |
invalid value for '--ask-for-approval' | Invalid approval value | Use: untrusted, on-failure, on-request, never |
unexpected argument after resume | Options after resume | Place options BEFORE resume subcommand |
cwd is not absolute | Windows absolute path | Use relative paths or cd first |
No prompt provided via stdin | Empty prompt | Ensure prompt string is not empty |
| Task Type | Recommended Timeout | Claude Code Tool |
|---|---|---|
| Quick checks | 2 minutes | timeout: 120000 |
| Standard review | 5 minutes | timeout: 300000 |
| Deep analysis | 10 minutes | timeout: 600000 |
Recommendation: Use timeout: 600000 for all Codex exec commands (model_reasoning_effort=high/xhigh can take 3-7 minutes).
codex exec in Claude Code and CI environments (non-TTY)-s read-only for all review tasksresume to maintain session context--add-dir for cross-project context--full-auto only in controlled environments--skip-git-repo-check - explain implicationsuntrusted/on-failure/on-request/nevertimeout: 600000)npx claudepluginhub creator-hian/claude-code-plugins --plugin codex-pluginRuns Codex CLI tasks with configurable model, reasoning effort, and sandbox mode. Handles session resume and stdin redirection to prevent hangs.
Executes Codex CLI (codex exec, resume) for code analysis, review, and automated editing with model selection (gpt-5.3-codex), sandbox modes, and git integration.
Executes Codex CLI for code analysis, refactoring, and automated edits with structured JSON output, file references, and sandbox controls.