npx skills add ...
npx skills add reason-machines/codex-skills --skill codex-redteam-mode
Opt-in red team mode for AI coding assistants that enables security-focused thinking for penetration testing and red team operations
npx skills add reason-machines/codex-skills --skill codex-redteam-mode
Skill by ara.so — Codex Skills collection.
Codex Red Team Mode is a lightweight, opt-in configuration layer that enables AI coding assistants to think like red team operators during authorized security assessments. Unlike persistent jailbreaks that pollute normal operations, this project provides:
phase -> router -> pack -> leaf workflow for security operationsThe project supports multiple security phases including web exploitation, Active Directory, post-exploitation, reverse engineering, code auditing, payload development, and evasion techniques.
The installer uses managed incremental installation that preserves your existing configuration while injecting only the necessary red team components.
The installer will:
AGENTS.md and hooks.jsonAfter installation, verify the setup:
| Mode | Default | Use Case |
|---|---|---|
normal | ✓ | Regular coding, documentation, general research |
redteam-light | Targeted security analysis, planning, threat modeling | |
redteam-full | Deep red team workflow with full routing |
The routing mainline follows:
"""
The mode state is stored in JSON format, typically in:
Example state file:
The hooks.json file manages prompt overlays:
To add custom phases, edit the routing configuration:
If normal mode feels influenced by red team prompts:
⚠️ Authorization Required: Only use red team mode on systems where you have explicit written authorization.
Never:
/redteam off when switching contextsSee CONTRIBUTING.md in the repository for guidelines on:
MIT License - See LICENSE file for details.*
# Ensure Python 3 is available
python3 scripts/install.py# Run validation script
python scripts/validate.py
# Or run full test suite
python -m unittest discover -s tests -p "test_*.py"# Full command
/redteam on
# Light mode (targeted security analysis)
/redteam light
# Full mode (complete red team workflow)
/redteam full
# Natural language
enable red team mode
Enter Red Team Mode# Command
/redteam off
# Natural language
disable red team mode
Exit Red Team Mode# Query current state
what mode am I in?
show red team statusphase -> router -> pack -> leaf# In red team mode, analyze a web application
"""
/redteam full
I need to assess a web application at https://target.example.com (authorized)
Focus on:
- Authentication mechanisms
- Session management
- Input validation
- API endpoints
"""
# The AI will route through: web -> api -> injection -> leaf
# Providing structured analysis with appropriate techniques# Enable red team mode for AD testing
"""
/redteam full
Analyzing Active Directory environment (authorized pentest)
- Domain: corp.example.local
- Current access: low-privilege domain user
- Goal: privilege escalation paths
"""
# Routes through: ad -> enum -> privesc -> pack# Light mode for code review
"""
/redteam light
Review this authentication function for security issues:def authenticate(username, password):
query = f"SELECT * FROM users WHERE username='{username}' AND password='{password}'"
result = db.execute(query)
return result.fetchone()