Claude.md
A plain markdown file at the root or project level inside Claude Code that stores rules, brand guidelines, coding standards, and project instructions, automatically loaded into every session as a system prompt
As defined in Every Claude Code Memory System Compared (So You Don't Have To)
Other definitions
The Claude-specific equivalent of agents.md; a markdown file for defining system instructions and context that are automatically provided to the Claude model.
Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems
Where it comes up · 5
- Every Claude Code Memory System Compared (So You Don't Have To)3 claims
- Every Claude Code Workflow Explained (& When to Use Each)2 claims
- The 7 Levels of Claude Code & RAG2 claims
- Andrej Karpathy Just 10x’d Everyone’s Claude Code2 claims
- Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems1 claim
Most important claims · 10 of 10Search all claims for “Claude.md” →
- Instructions are the first harness primitive; they tell the model who it is, what work it does, the tone, constraints, coding style, code review rules, and actions to avoid. Examples include agents.md, claude.md, system prompts, custom instructions, repository rules, and cursor rules. Instructions move repeated guidance into the environment so users don't have to repeat them.Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems
- Claude.md files, when referenced in every prompt, can actually reduce the effectiveness of large language models at large according to studies evaluating agent.md files, because injecting the same context into every prompt creates noise rather than signal if that context isn't universally relevant.The 7 Levels of Claude Code & RAG
- Claude.md is a plain markdown file inside a project folder where you store rules, brand information, client details, and coding style, and it is always loaded into every single Claude Code session in the terminal, functioning like a system prompt given to Claude.Every Claude Code Memory System Compared (So You Don't Have To)
- The multi-file architecture approach with specialized files (project, requirements, roadmap, state) fights against context rot by avoiding the injection of all files into every prompt like Claude.md does, and creates a clear navigation hierarchy for Claude Code to follow.The 7 Levels of Claude Code & RAG
- Context rot is the inability for AI and LLM models to recall 100% of information that has been loaded in as the amount of context loaded increases, and as a general rule of thumb, you should keep your claude.md file under 200 lines to avoid it.Every Claude Code Memory System Compared (So You Don't Have To)
- The system creates different folder structures (analysis, concepts, entities, sources) within the wiki by default, which can be modified based on project needs.Andrej Karpathy Just 10x’d Everyone’s Claude Code
- For someone literally just starting with Claude Code, don't worry about memory systems and just turn on Level 1 (claude.md and memory.md files) which takes 10 minutes and is a massive improvement on inbuilt memory.Every Claude Code Memory System Compared (So You Don't Have To)
- Skills and commands (like `/clear` and `/compact`) are valuable tools in sequential flow to load reference files at the right time and offload them afterward, preventing context bloat and extending the useful lifespan of a single session before hitting the context window ceiling.Every Claude Code Workflow Explained (& When to Use Each)
- A Claude.md file documents how the project works, how to search through things, and how to update the wiki, serving as comprehensive documentation for the system.Andrej Karpathy Just 10x’d Everyone’s Claude Code
- The Agentic Academy (linked in the video description) offers a full Claude Code track that covers building skills, creating custom sub-agents, structuring Claude.md, and putting the five patterns into practice with real projects.Every Claude Code Workflow Explained (& When to Use Each)