Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Agent instructions file (AGENTS.md)

An agent instructions file is a Markdown file in a code repository, such as AGENTS.md or CLAUDE.md, that a coding agent reads at the start of a session to learn the project's commands, conventions and rules.

Also called: AGENTS.md, CLAUDE.md, .cursorrules, rules file

By Divya Sharma · Checked Nov 15, 2026 · How we review

A coding agent starts each session knowing nothing about your project. Without help, it guesses how to run the tests, which style to follow and which folders to leave alone. An instructions file answers those questions once, in a place the agent always reads.

The common formats

AGENTS.md is an open format meant to work across tools, and is read by OpenAI Codex and many others. Claude Code reads CLAUDE.md and can also use AGENTS.md. Cursor has its own rules files, including the older .cursorrules. The content is similar everywhere: build and test commands, code style, architecture notes, and things not to do.

How it works

The agent loads the file into its context at the start of a session, so it acts like a project-level system prompt. Files can be nested: a monorepo can keep one at the root and another in each package, and the AGENTS.md guidance is that the closest file to the code being edited wins, while instructions typed in chat override all of them. A personal file in your home folder can hold rules that apply to every project.

Limits

The file is context, not enforcement. The agent usually follows it but can ignore or forget it, especially after context compaction. Rules that must always hold, such as never touching a production config, belong in agent hooks or permission settings. Keep the file short and specific; long files cost tokens every session and dilute the rules that matter. Reusable procedures fit better in agent skills.

Related terms

Coding agent
A coding agent is an AI agent that works on software directly: it reads a codebase, edits files, runs commands and tests, and repeats until a change works, rather than only suggesting code for a person to paste.
Context engineering
Context engineering is the practice of choosing and maintaining everything that goes into a language model's context window during a task: instructions, retrieved documents, tool definitions, tool results and conversation history.
Agent skills
Agent skills are folders of instructions, scripts and reference files, each described by a SKILL.md file, that an AI agent can discover and load only when a task needs them.
Agent hooks
Agent hooks are user-defined commands or scripts that a coding agent runs automatically at set points in its work, such as before a tool call or after a file edit, to check, block or extend what it does.
System prompt
A system prompt is the block of instructions an application sends to a language model before the user's messages. It sets the model's role, rules, tone and output format for the whole conversation.
Slash command
A slash command is an instruction typed with a leading slash, such as /compact or /review, that tells an AI tool to run a built-in action or a saved prompt instead of treating the text as an ordinary message.

Sources