Claude-skill-registry codex-cli
OpenAI Codex CLI fundamentals for code analysis, review, and validation. Use when (1) executing codex commands for code review/analysis, (2) configuring models (gpt-5.2-codex/gpt-5.2/gpt-5.1-codex-max/codex-mini), sandbox modes (read-only/workspace-write), or reasoning effort (low/medium/high/xhigh), (3) managing Codex sessions with resume, (4) integrating Codex into automation scripts. Do NOT use for orchestration patterns (use codex-claude-loop instead).
git clone https://github.com/majiayu000/claude-skill-registry
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/codex-cli" ~/.claude/skills/majiayu000-claude-skill-registry-codex-cli-3be91d && rm -rf "$T"
skills/data/codex-cli/SKILL.mdCodex CLI Skill
⚠️ Environment Notice
| Environment | Git Repo | Command Format |
|---|---|---|
| Interactive terminal | Any | |
| Claude Code / CI | ✅ Yes | |
| Claude Code / CI | ❌ No | |
Non-TTY environments (Claude Code, CI pipelines, scripts) require
codex exec.
Git Repository Detection
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"
- Git repo exists: Use standard commands
- No Git repo: Add
flag (requires user awareness of security implications)--skip-git-repo-check
Quick Start
In Git Repository (Standard)
# 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-5.2-codex -c model_reasoning_effort=high "Deep analysis" # With image input codex exec -s read-only -i screenshot.png "What's shown here?"
Outside Git Repository
# 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-5.2-codex "Deep analysis"
Session Resume (Special Syntax)
# 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"
Reference Documentation
- Commands Reference -
,codex
,resume
, input/output patternsapply - Options Reference - Models, sandbox, reasoning effort, approval modes
- Examples - Code review, security analysis, automation scripts
Available Models
Full model details: See Options Reference
| Model | Best For |
|---|---|
| Complex analysis, critical systems (recommended) |
| General AI tasks, multi-domain |
| Security audits, architecture review |
| Quick checks, batch operations |
Reasoning Effort
Usage examples: See Options Reference
| Level | Use Case |
|---|---|
| Simple checks, syntax review |
| Standard code review (default) |
| Security audits, complex logic |
| Critical systems, exhaustive analysis |
Sandbox Modes
| Mode | Description |
|---|---|
| Cannot modify files (safest, recommended) |
| Can modify workspace files |
| Full system access (use sparingly) |
Key Options
Full options list: See Options Reference
Common Patterns
Full examples: See Examples for detailed patterns
Essential Patterns
# Code review (Claude Code/CI) codex exec -s read-only "Review: $(cat src/auth.js)" # Maximum depth analysis codex exec -m gpt-5.2-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"
Platform-Specific Notes
Windows Limitations
| Issue | Description | Workaround |
|---|---|---|
with absolute paths | error with Windows paths like | Use relative paths () 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 Handling
Error recovery patterns: See Examples
| Error | Cause | Solution |
|---|---|---|
| Using in non-TTY | Use |
| Not in Git repo | Ask user, then use |
| Invalid approval value | Use: , , , |
after | Options after | Place options BEFORE subcommand |
| Windows absolute path | Use relative paths or first |
| Empty prompt | Ensure prompt string is not empty |
Timeout Configuration
| Task Type | Recommended Timeout | Claude Code Tool |
|---|---|---|
| Quick checks | 2 minutes | |
| Standard review | 5 minutes | |
| Deep analysis | 10 minutes | |
Recommendation: Use
timeout: 600000 for all Codex exec commands (model_reasoning_effort=high/xhigh can take 3-7 minutes).
Best Practices
- Use
in Claude Code and CI environments (non-TTY)codex exec - Default to
for all review tasks-s read-only - Match model + reasoning effort to task complexity
- Use
to maintain session contextresume - Use
for cross-project context--add-dir - Use
only in controlled environments--full-auto - Ask user before
- explain implications--skip-git-repo-check - Check valid approval values - only use
/untrusted
/on-failure
/on-requestnever - Set 10-minute timeout for all Codex exec commands (
)timeout: 600000