Drive Anthropic's Claude Code CLI (claude -p) as a non-interactive coding sub-agent from inside Codex. Use when you want to delegate a coding/analysis/refactor task to Claude, get a second opinion / adversarial review from another model, hand off long-context planning, or fan out parallel agents. Covers the exact claude -p flags, permission modes, output capture, JSON/stream-json modes, session resume, parallel fan-out, and the mandatory "delegate → capture → independently verify, never trust the self-report" supervision loop.
$npx -y skills add kortix-ai/suna --skill claude-cliInstalls into the current project.
Run `npx skills use "https://github.com/kortix-ai/suna" --skill "kortix-ai/suna/claude-cli"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/kortix-ai/suna" that are relevant to the current task. Run `npx skills add "https://github.com/kortix-ai/suna"` and select the relevant skills, then follow their instructions.