https://blog.margrop.net/en/tag/aider/ Recent content in Aider on Margrop Blog Hugo -- gohugo.io en-US Mon, 06 Jul 2026 09:50:00 +0800 https://blog.margrop.net/en/post/ai-agent-yolo-one-command/ Mon, 06 Jul 2026 09:50:00 +0800 https://blog.margrop.net/en/post/ai-agent-yolo-one-command/ <blockquote> <p><strong>Short version</strong></p> <p>In AI Agent tools, <code>yolo</code> does not mean “the model is smarter.” It means “ask me fewer questions.” It reduces or skips approval prompts so the Agent can run more like an unattended automation script. The annoying part is that every tool names this differently. Codex exposes a dangerous approval-and-sandbox bypass. Claude Code has a dangerous permission-skip mode and a permission mode. Gemini CLI and Qwen Code use <code>--approval-mode=yolo</code>. OpenCode uses <code>--auto</code> plus permission rules. Aider uses <code>--yes-always</code>.</p> <p>My recommendation is not to overwrite <code>codex</code>, <code>claude</code>, or <code>gemini</code> with risky aliases. Install an explicit <code>agent-yolo</code> launcher instead. When you really want high autonomy, type <code>agent-yolo codex</code>, <code>agent-yolo claude</code>, or <code>agent-yolo gemini</code>. This article provides Windows 11, Ubuntu 26.04, and macOS 26 scripts. They do not depend on third-party services, do not install missing Agent tools, and do not contain private addresses, full computer names, private domains, tokens, or keys.</p> </blockquote>