codex-orchestrator

name	codex-orchestrator
description	Spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, and documentation via AGENTS.md persona injection (gpt-5.5, gpt-5.5-pro, gpt-5-mini). Triggers on 'delegate to Codex', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex'.

Codex Orchestrator

Spawn specialized Codex CLI subagents for focused development tasks. Each profile injects a custom AGENTS.md persona that shapes the agent's behavior, focus areas, and output format.

Architecture

Claude Code (orchestrator)
    ↓ invokes skill
codex-orchestrator scripts
    ↓ spawns via Bash
Codex CLI with AGENTS.md
    ↓ executes
Specialized subagent task

Prerequisites

Verify Codex CLI is installed and configured:

~/.claude/skills/codex-orchestrator/scripts/codex-status.sh

Required:

• Codex CLI: npm install -g @openai/codex
• API Key: export OPENAI_API_KEY=sk-...

Auto-Update

The skill automatically checks for Codex CLI updates on each invocation and updates if needed. This prevents issues caused by outdated CLI versions.

To manually check/update:

# Check version only
~/.claude/skills/codex-orchestrator/scripts/codex-version-check.sh

# Check and auto-update if needed
~/.claude/skills/codex-orchestrator/scripts/codex-version-check.sh --auto-update

Available Profiles

Profile	Purpose	Use When
reviewer	Code quality, bugs, performance	Pre-commit review, PR assessment
debugger	Root cause analysis, fixes	Investigating bugs, tracing issues
architect	System design, component boundaries	Planning changes, evaluating architecture
security	OWASP, vulnerabilities, secrets	Security audits, compliance checks
refactor	Code cleanup, modernization	Reducing tech debt, improving structure
docs	API docs, READMEs, comments	Documentation tasks
planner	ExecPlan design documents	Multi-hour tasks, complex features, significant refactors
syseng	Infrastructure, DevOps, CI/CD, monitoring	Deployment, containers, observability, production ops
builder	Greenfield implementation, new features	Creating new code from specs, incremental feature development
researcher	Read-only Q&A, codebase analysis	Questions, analysis, comparisons (no file changes)
chat	Open-ended conversation	General questions, brainstorming, discussion (read-only, ephemeral)

Quick Execution

Execute a one-shot task with a specific profile:

~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh <profile> "<prompt>"

Examples:

# Code review
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh reviewer "Review src/auth.ts for security issues"

# Debug investigation
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh debugger "Debug the login timeout on slow networks"

# Architecture design
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh architect "Design a caching layer for the API"

# Security audit
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh security "Audit the payment module for vulnerabilities"

# Write profiles auto-approve by default (uses -a never + --sandbox workspace-write)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh reviewer "Fix all lint errors"

# Create execution plan for complex feature
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh planner "Create an ExecPlan for adding WebSocket support"

# Build new feature from spec
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "Implement user authentication with JWT"

# Continue from previous builder session
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "continue"

# Open-ended conversation (read-only, ephemeral, gpt-5.4 via subscription)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "What are the tradeoffs of event sourcing vs CRUD?"

# Conversation via API billing (gpt-5.5, bypasses Codex subscription)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "Explain quantum error correction" --api --model gpt-5.5

# Multi-turn API chat with session file
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "What is the tallest mountain?" --api --session /tmp/chat.json
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "And the deepest ocean?" --api --session /tmp/chat.json

# Streaming API response
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "Tell me about CQRS" --api --model gpt-5.5 --stream

# Ask a question about the codebase (read-only, no file changes)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh researcher "Explain the authentication flow in this project"

# Research with Exa web search (injects Exa guide into AGENTS.md)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh researcher "What are the latest React Server Component patterns?" --web-search

# Research with native Codex web search (model-level tool, works in all sandboxes)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh researcher "What are the latest React patterns?" --search

# Review a screenshot (vision input)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh reviewer "Review this mockup for UX issues" --image screenshot.png

# Resume previous builder session
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "continue" --resume

# JSONL output for structured capture
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh researcher "What is 2+2?" --json | head -5

Session Management

For more control, use the Python session manager:

# List available profiles
python3 ~/.claude/skills/codex-orchestrator/scripts/codex-session.py list

# Start non-interactive session
python3 ~/.claude/skills/codex-orchestrator/scripts/codex-session.py start debugger "Trace the null pointer in UserService"

# Start interactive session
python3 ~/.claude/skills/codex-orchestrator/scripts/codex-session.py interactive architect

# Show profile details
python3 ~/.claude/skills/codex-orchestrator/scripts/codex-session.py info security

Profile Selection Guide

Review Tasks

• reviewer for general code quality and bugs
• security for vulnerability-focused review
• refactor for cleanup opportunities

Investigation Tasks

• debugger for bug investigation
• architect for understanding system behavior
• researcher for questions and analysis (read-only, no changes)
• chat for open-ended conversation and brainstorming (read-only, ephemeral)

Creation Tasks

• architect for design decisions
• builder for new feature implementation
• docs for documentation
• refactor for implementation improvements
• planner for multi-hour implementation plans

Chaining Patterns

Review → Debug → Fix

# 1. Identify issues
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh reviewer "Review src/api/ for bugs"

# 2. Investigate specific bug
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh debugger "Debug the race condition found in cache.ts"

Planner → Architect → Builder

# 1. Create comprehensive ExecPlan
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh planner "Create ExecPlan for new authentication system"

# 2. Validate architecture
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh architect "Review the auth system ExecPlan for design issues"

# 3. Build (plan guides implementation)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "Implement milestone 1 from the auth ExecPlan"

Architect → Builder → Reviewer

# 1. Design approach
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh architect "Design a caching layer for the API"

# 2. Build the feature
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "Implement the caching layer from architect's design"

# 3. Review the implementation
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh reviewer "Review the new caching implementation"

Architect → Review → Refactor

# 1. Design approach
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh architect "Design repository layer extraction"

# 2. Validate design
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh reviewer "Review the proposed repository pattern"

# 3. Implement
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh refactor "Extract repository pattern from services"

Syseng → Architect → Planner

# 1. Assess infrastructure needs
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh syseng "Evaluate current deployment for scaling to 10x traffic"

# 2. Design architecture changes
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh architect "Design infrastructure to support 10x scale"

# 3. Create implementation plan
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh planner "Create ExecPlan for infrastructure scaling"

Security → Syseng

# 1. Security audit
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh security "Audit the Kubernetes cluster configuration"

# 2. Infrastructure hardening
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh syseng "Implement security recommendations from audit"

Researcher → Architect → Builder

# 1. Understand the problem space
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh researcher "How does the current caching work? What are its limitations?"

# 2. Design the solution
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh architect "Design a new caching layer addressing the limitations"

# 3. Implement
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "Implement the caching layer from architect's design"

Script Options

codex-exec.sh Options

Option	Description
--model <model>	Override model (default: per-profile, see below)
--reasoning <level>	Override reasoning effort: minimal, low, medium, high, xhigh
--sandbox <mode>	read-only, workspace-write, danger-full-access
--no-approve	Force read-only sandbox (no file writes)
--web-search	Enable Exa web search (injects guide into AGENTS.md)
--search	Enable native Codex web search (model-level tool, works in all sandboxes)
--json	Output JSONL event stream (pipe to jq, logs, etc.)
--image <file>	Attach image to prompt (vision input)
--resume	Resume previous exec session (builder "continue" workflow)
--with-mcp	(no-op, kept for compatibility; manage MCPs in ~/.codex/config.toml)
--api	Use OpenAI API directly (API billing, not Codex subscription)
--session <file>	Session file for multi-turn API chat (requires --api)
--system <prompt>	System prompt for API chat (requires --api)
--stream	Stream API response tokens (requires --api)

Model & Reasoning Defaults

Each profile has a default model and reasoning effort. User flags override these.

Profile Type	Profiles	Model	Reasoning
Coding	builder, reviewer, debugger, refactor, syseng, security, docs	gpt-5.5	high
Planning	planner, architect	gpt-5.5	high
Research	researcher	gpt-5.5	medium
Chat	chat	gpt-5.4	medium

Reasoning effort levels: none < minimal < low < medium < high < xhigh

# Uses profile defaults (builder → gpt-5.5 + high)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "Implement auth module"

# Uses profile defaults (planner → gpt-5.5 + high)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh planner "Create ExecPlan for caching"

# Override model for quick tasks
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh reviewer "Style check" --model gpt-5-mini

# Override reasoning only
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh builder "Quick lint fix" --reasoning medium

# Override both
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh planner "Design distributed cache" --model gpt-5.5 --reasoning high

API Mode (Direct OpenAI API)

The --api flag bypasses Codex CLI entirely and calls the OpenAI API directly via gpt-api-chat.py. Billing goes to your OPENAI_API_KEY, not the Codex subscription.

When to use API mode:

• Access models not in your Codex subscription (e.g. gpt-5.5)
• Multi-turn conversations with session persistence
• Streaming responses
• Custom system prompts

# One-shot API query
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "Explain X" --api --model gpt-5.5

# Multi-turn with session file (context carries across calls)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "What is X?" --api --session /tmp/session.json
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "Tell me more" --api --session /tmp/session.json

# Streaming output
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "Describe Y" --api --model gpt-5.5 --stream

# Custom system prompt
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh chat "Analyze this" --api --system "You are a security analyst"

# Any profile works with --api (sends raw prompt to OpenAI API, no Codex CLI)
~/.claude/skills/codex-orchestrator/scripts/codex-exec.sh researcher "What are the latest React patterns?" --api --model gpt-5.5

Supported models: gpt-5.5, gpt-5.5-pro, gpt-5.4, gpt-5-mini, o3, o4-mini, o3-mini, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini, gpt-4-turbo

Three-way mode (Claude + GPT): Within a Claude Code session, invoke gpt-api-chat.py via Bash, read GPT's response, synthesize perspectives, and steer the conversation. Use --session to maintain GPT's context across turns.

Requires: OPENAI_API_KEY in environment (loaded from ~/.config/env/secrets.env)

Testing

Run the test suite to verify installation:

~/.claude/skills/codex-orchestrator/scripts/test-codex.sh         # Full tests
~/.claude/skills/codex-orchestrator/scripts/test-codex.sh --quick # Skip API test

Reference Documentation

For detailed information:

• references/codex-cli.md - Complete CLI command reference
• references/agents-md-format.md - AGENTS.md syntax and best practices
• references/subagent-patterns.md - Delegation patterns and examples

Troubleshooting

"Codex CLI not found"

npm install -g @openai/codex

"Authentication error"

export OPENAI_API_KEY=sk-...
# or
codex login

"Model not supported with ChatGPT account"

Older model names (codex-mini, o3, o4-mini) have been deprecated. Current models: gpt-5.5, gpt-5.5-pro, gpt-5-mini, gpt-5-nano. Previous generation (gpt-5.4, gpt-5.4-pro, gpt-5.3-codex, gpt-5.2) still works but is superseded. Set an API key instead of using codex login:

export OPENAI_API_KEY=sk-...

"Profile not found"

Available profiles: reviewer, debugger, architect, security, refactor, docs, planner, syseng, builder, researcher, chat

Check profile exists:

ls ~/.claude/skills/codex-orchestrator/agents/

"Codex produced no output"

The researcher/chat profiles capture output to a temp file. If Codex exits without writing to it, the script warns and exits 1. Common causes:

• Codex session too short to produce a response
• Model returned empty response (retry)
• AGENTS.md was missing (check for stale .AGENTS.md.codex-backup.* files in working directory)

Poor Results

• Narrow the task scope
• Provide more context in the prompt
• Try a different profile
• Use --model gpt-5.5-pro for complex tasks