long-running-project-memory

Design, audit, or repair scalable memory systems for long-lived software projects. Use when Codex needs to organize agent instructions, runbooks, handoffs, project memory, changelogs, recovery docs, or multi-agent continuity; prevent stale facts from overriding current state; reduce startup context; or add enforcement for project memory discipline.

Design, audit, or repair a repo-backed memory system for long-lived agent continuity. Use when the user asks about agent instructions, runbooks, task state, resume packets, topic memory, plans, structured history, cross-session continuity, stale facts, or memory-system enforcement.