Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.
2 files for Codex, OpenCode and Claude Code: ai-reliability-copilot AGENTS.md, ai-reliability-copilot CLAUDE.md — 4,504 tokens loaded in every session.
AGENTS.md A 74 tok CLAUDE.md C 4,430 tok These files are YanpengQi7/ai-reliability-copilot'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.