codex-redteam-mode for Red Team Attacks
Codex-redteam-mode provides a red team mode for penetration testing, allowing founders to simulate attacks and test their AI systems' defenses using Python
- •When you need to test the security of your AI system against potential attacks
- •When you want to identify vulnerabilities in your AI model's architecture
- •When you need to train your AI model to defend against common attack vectors
python redteam_mode.py --agent=my_agent --target=my_ai_system
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/codex-redteam-mode && curl -fsSL https://workflowstacks.com/api/skills/codex-redteam-mode/claude-skill -o ~/.claude/skills/codex-redteam-mode/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Codex-redteam-mode for Red Team Attacks is a medium Python project (~10k lines across 30 code files, plus 5 test files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit this month, MIT license, has a test suite.
- 1README.mdStart here — what it does and how to install it
- 2requirements.txtDependencies and the commands it exposes
- 3agents/skills/redteam-boundary-policy/SKILL.mdInside agents/ — an example of what the AI is told to do
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/codex-redteam-mode && curl -fsSL https://workflowstacks.com/api/skills/codex-redteam-mode/claude-skill -o ~/.claude/skills/codex-redteam-mode/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? Claim your listing → and earn 85% of every sale.
Related skills
More devtools tools founders pair with this one.