# Repository-Scoped Instructions Repository-scoped instructions place durable project guidance beside the source, documents, tests, and artifacts it governs. The repository becomes not only a code container but a self-describing operational environment for people and agents. This matches the broader X/XApps principle that the complete thought should travel in the folder. Modern files such as `AGENTS.md`, `CLAUDE.md`, skill directories, contracts, and fixtures make that principle legible to AI tools. Related: [[wiki/Hierarchical Instruction Files|Hierarchical Instruction Files]], [[wiki/Filesystem-Based Agent Skills|Filesystem-Based Agent Skills]], [[projects/X and XApps - Drop the Folder and It Runs|X and XApps]]. Sources: [OpenAI — `AGENTS.md`](https://developers.openai.com/codex/guides/agents-md), [Anthropic — Claude Code memory](https://docs.anthropic.com/en/docs/claude-code/memory)