Autonomous software delivery for AI agents. 18 skills that turn the lifecycle into bounded, self-correcting, checkpoint-resumable phases with deterministic enforcement hooks and a self-improving learn/map loop. For Claude Code and Codex.
2 files for Codex, OpenCode and Claude Code: autonomous-engineering AGENTS.md, autonomous-engineering CLAUDE.md — 5,042 tokens loaded in every session.
AGENTS.md A 3,095 tok CLAUDE.md A 1,947 tok These files are ulpi-io/autonomous-engineering'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.