The Never List
A safety manifest and context pattern for AI agents operating in knowledge vaults.
byCyrilXBT
Is this your creation?
Description
An architecture for a 'CLAUDE.md' manifest file that provides persistent context and safety constraints to AI agents (like Claude Code) operating within Obsidian vaults. The system uses a 'Never List'—a set of rules that prevent the agent from deleting files, restyling content, or breaking backlinks—ensuring autonomous agents can manage tasks and notes without compromising the integrity of a long-term knowledge base.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.