An engineering philosophy that treats the agent as a worker: the system prompt is a JD, skills are certifications, model tiers are degrees, memory is a career record, the sandbox is a work computer. Bilingual, 中文/English.
2 files for Codex, OpenCode and Claude Code: agent-engineering-philosophy AGENTS.md, agent-engineering-philosophy CLAUDE.md — 3,476 tokens loaded in every session.
AGENTS.md A 1,738 tok CLAUDE.md A 1,738 tok These files are Onenightcarnival/agent-engineering-philosophy'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.