Testing an AI Memory Reliability Checklist on 3 Redacted Agent Setups

I’m testing a small AI memory reliability checklist. The question is simple: When an AI agent reads project instructions, memory files, Cursor rules, or AGENTS.md before acting, can we tell which instructions should actually govern action? I’m looking for 3 people who use Claude, Cursor, Codex, or custom agents and are willing to share redacted, non-sensitive instruction files.