.claude/skills/codex-chat/SKILL.md
Interactive REPL workflows with Codex CLI including session management, multimodal conversations, and automated execution. Use for extended development sessions, debugging, or collaborative problem-solving.
npx skillsauth add adaptationio/skrillz codex-chatInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Advanced interactive workflows with Codex CLI REPL featuring full automation and session management.
Last Updated: December 2025 (GPT-5.2 Release)
# Start interactive session
codex "Let's work on improving authentication"
# With full automation
codex --dangerously-bypass-approvals-and-sandbox "Auto-execute everything"
# With specific model (December 2025)
codex -m gpt-5.1-codex-max "Complex development task" # Default, best for coding
codex -m gpt-5.2 "Tasks needing 400K context"
codex -m gpt-5.2-pro "Maximum accuracy tasks"
# With images
codex -i design.png "Implement this UI design"
# With web search
codex --search "Research and implement OAuth2"
# Full auto development session (December 2025)
codex --dangerously-bypass-approvals-and-sandbox \
-m gpt-5.1-codex-max \
--search \
"Build complete user authentication system"
# With GPT-5.2 for long-context tasks
codex --dangerously-bypass-approvals-and-sandbox \
-m gpt-5.2 \
--compact \
"Analyze entire codebase and refactor"
# Sandboxed automation
codex --full-auto "Refactor safely with tests"
# Resume last session
codex exec resume --last
# Pick session to resume
codex resume
# Apply latest changes from session
codex apply
# or
codex a
# With single image
codex -i mockup.png --dangerously-bypass-approvals-and-sandbox \
"Implement this design perfectly"
# With multiple images
codex -i design1.png -i design2.png --full-auto \
"Compare and implement best approach"
#!/bin/bash
# Automated feature development session (December 2025)
dev_session() {
local feature="$1"
codex --dangerously-bypass-approvals-and-sandbox \
--search \
-m gpt-5.1-codex-max \
"Feature: $feature
Execute automatically:
1. Research best practices
2. Create implementation plan
3. Generate all code
4. Write comprehensive tests
5. Run tests and fix failures
6. Generate documentation
7. Create git commits
8. Summarize changes"
}
# For complex tasks requiring high accuracy
dev_session_pro() {
local feature="$1"
codex --dangerously-bypass-approvals-and-sandbox \
-m gpt-5.2-pro \
--reasoning-effort xhigh \
"Feature: $feature - Implement with maximum accuracy"
}
# Usage
dev_session "user profile caching"
dev_session_pro "payment processing system"
codex-cli: Main integrationcodex-auth: Authenticationcodex-tools: Tool executioncodex-review: Code reviewcodex-git: Git workflowsdevelopment
Setup secure web-based terminal access to WSL2 from mobile/tablet via ttyd + ngrok/Cloudflare/Tailscale. One-command install, start, stop, status. Use when you need remote terminal access, web terminal, browser-based shell, or mobile access to WSL2 environment.
development
Complete development workflows where Claude writes the code while Gemini and Codex provide research, planning, reviews, and different perspectives. Claude remains the main developer. Use for complex projects requiring expert planning and multi-perspective reviews.
development
Systematic progress tracking for skill development. Manages task states (pending/in_progress/completed), updates in real-time, reports progress, identifies blockers, and maintains momentum. Use when tracking skill development, coordinating work, or reporting progress.
testing
Comprehensive testing workflow orchestrating functional testing, example validation, integration testing, and usability assessment. Sequential workflow for complete skill testing from examples through scenarios to integration validation. Use when conducting thorough testing, pre-deployment validation, ensuring skill functionality, or comprehensive quality checks.