Harness-driven terminal AI agent for authorized security assessment, with TUI, headless automation, persistent context, 150 built-in skills, and a dedicated pentest mode.
2 files for Codex, OpenCode and Claude Code: Mingyi-Atlas AGENTS.md, Mingyi-Atlas CLAUDE.md — 5,990 tokens loaded in every session.
AGENTS.md A 3,930 tok CLAUDE.md A 2,060 tok These files are MingyiSecLab/Mingyi-Atlas's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.