For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
安装
npx skills add tjboudreaux/cc-thinking-skills --skill thinking-red-teamnpx skills add tjboudreaux/cc-thinking-skills --skill thinking-red-team -a claude-code -gnpx skills add tjboudreaux/cc-thinking-skills --skill thinking-red-team -a codex -ggemini skills install https://github.com/tjboudreaux/cc-thinking-skills.git --path skills/thinking-red-teamgh skill install tjboudreaux/cc-thinking-skills thinking-red-teamgit clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills /tmp/tjboudreaux__cc-thinking-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/tjboudreaux__cc-thinking-skills/skills/thinking-red-team ~/.claude/skills/thinking-red-team # Claude Code
cp -R /tmp/tjboudreaux__cc-thinking-skills/skills/thinking-red-team ~/.agents/skills/thinking-red-team # Codex, Cursor, Gemini CLI, Copilot, OpenCode