14 questions people ask about RuleStack.
Every answer below already renders on a comparison page of this site, and each one quotes the vendor documentation it came from. Nothing here was written for this page.
Does Claude Code read AGENTS.md?
No. Anthropic's memory documentation states it directly: "Claude Code reads CLAUDE.md, not AGENTS.md." The documented fix is not to duplicate the file but to import it, "create a CLAUDE.md that imports it so both tools read the same instructions without duplicating them", after which Claude-specific instructions can be appended below the import. A symlink is documented as the alternative where you have nothing Claude-specific to add, with the caveat that on Windows a symlink needs administrator privileges or developer mode.
Can I use AGENTS.md and CLAUDE.md at the same time?
Yes, and the import path is the documented way to do it without maintaining two copies of the same prose. A CLAUDE.md whose first line is an @-import of AGENTS.md loads the imported file at session start and then appends whatever else the file says. Anthropic's page shows exactly that arrangement. GitHub documents a third variation on the same idea: Copilot reads AGENTS.md files "stored anywhere within the repository" and, alternatively, "a single CLAUDE.md or GEMINI.md file stored in the root of the repository", so a repository carrying both is a repository every one of those three agents can read.
Which one should I use in a monorepo?
Either, they resolve nesting the same way, and the difference is when the files load rather than which one wins. AGENTS.md says "agents automatically read the nearest file in the directory tree, so the closest one takes precedence", and cites the main OpenAI repository as carrying 88 of them. Anthropic's page says Claude "discovers CLAUDE.md and CLAUDE.local.md files in subdirectories under your current working directory" but that "instead of loading them at launch, they are included when Claude reads files in those subdirectories", so a deep monorepo costs context only as it is touched. If you need a rule that loads on a file pattern rather than a directory, that is a third mechanism on the Claude side: .claude/rules/ files "can also be scoped to specific file paths".
How long should the file be?
Anthropic publishes a number and agents.md does not. The memory docs say "target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence", and point at path-scoped rules for anything larger. agents.md publishes no line count, no byte budget and no context-cost guidance at all; its sizing advice is editorial, "anything you'd tell a new teammate belongs here too". Of the five formats RuleStack tracks, only two publish a number: 200 lines for CLAUDE.md and 500 lines per rule for Cursor.
What happens when two instruction files disagree?
Both resolve it by proximity, and both say so. agents.md: "The closest AGENTS.md to the edited file wins; explicit user chat prompts override everything." Anthropic's docs describe the same outcome through load order rather than a winner, every discovered file is concatenated, "content is ordered from the filesystem root down to your working directory", so "instructions closer to where you launched Claude are read last", and within a directory CLAUDE.local.md is appended after CLAUDE.md.
Is .cursorrules deprecated?
Cursor's current rules documentation does not present a single .cursorrules file as the project format any more: it describes project rules as living "in .cursor/rules as .mdc files", and states that "a plain .md file in .cursor/rules is ignored by the rules system because it has no frontmatter to specify description, globs, and alwaysApply". Its file-tree example marks api-guidelines.md as "ignored (wrong extension)". Other vendors still read the old filename: Cline's supported-rule-types table lists .cursorrules as "Automatically detected", and Anthropic's docs say /init "reads Cursor rules, in .cursor/rules/ or .cursorrules". RuleStack tracks .cursorrules and .cursor/rules as separate formats for exactly this reason, and counts both nightly.
What is the alternative to Cursor rules that other agents can read?
AGENTS.md, and Cursor says so on its own rules page: it lists AGENTS.md as a rule type, "Simple alternative to .cursor/rules", and adds "If you prefer plain markdown, use AGENTS.md instead." It is also the format named as readable in the other vendors' documentation: GitHub's repository-instructions page documents Copilot reading "one or more AGENTS.md files, stored anywhere within the repository", and Cline's rules page lists it as the "Standard format for cross-tool compatibility". agents.md itself is "stewarded by the Agentic AI Foundation under the Linux Foundation".
Which format supports per-directory instructions?
Three of the five, and they are not equivalent. AGENTS.md is per-directory by design, "agents automatically read the nearest file in the directory tree, so the closest one takes precedence", and Cursor's page confirms it reads them "in the project root and subdirectories". CLAUDE.md files in subdirectories are discovered but load lazily: "instead of loading them at launch, they are included when Claude reads files in those subdirectories". Cursor's own rules and Copilot's instructions are centralised instead: Cursor's subfolders are documented as organisation ("organize rules in folders") and Copilot's extra files sit "within or below the .github/instructions directory", aimed at code by glob rather than by location. Cline's page documents no per-package rules directory at all.
How do I stop instruction files eating my context window?
Scope them, and only two of the five publish a budget to scope them against. Cursor: "Keep rules under 500 lines", split into composable rules. Anthropic: "target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence." AGENTS.md, Copilot instructions and Cline rules publish no number. All four of the non-AGENTS.md formats do publish a scoping mechanism, and they are worth knowing apart: Cursor uses globs plus a description the agent evaluates for relevance, Copilot uses an applyTo glob in frontmatter, Cline uses a paths list in frontmatter, and Claude uses .claude/rules/ files that "can also be scoped to specific file paths". AGENTS.md has no scoping field; its only lever is where you put the file.
Which instruction file wins when several apply?
Every one of the five publishes an answer and they are genuinely different, which is the thing to check before you assume. AGENTS.md and CLAUDE.md both resolve by proximity to the code. Cline resolves by scope: "Workspace rules take precedence when they conflict with global rules." Cursor resolves in favour of the organisation: team rules "take precedence to ensure organizational standards are maintained across all projects", and an enforced team rule "cannot be disabled in Customize". Copilot resolves the other way entirely, "Personal instructions take the highest priority. Repository instructions come next, and then organization instructions are prioritized last", while still sending every relevant set to the model.
Which agent instruction format should I use?
Start with AGENTS.md if more than one agent touches the repository. It is the only one of the five not owned by the tool that reads it, "stewarded by the Agentic AI Foundation under the Linux Foundation", and the vendors' own pages tell you to: Cursor writes "If you prefer plain markdown, use AGENTS.md instead", GitHub documents Copilot reading "one or more AGENTS.md files, stored anywhere within the repository", and Cline lists it as the "Standard format for cross-tool compatibility". Add a tool-specific file on top only when you need something AGENTS.md does not have: an import (CLAUDE.md), a glob-scoped rule (Cursor, Copilot, Cline), or a rule that applies to pull-request review on github.com (Copilot).
Do these formats replace each other or stack?
They stack, and every vendor documents the stacking rather than an either/or. Anthropic documents a CLAUDE.md that imports AGENTS.md "so both tools read the same instructions without duplicating them". GitHub documents Copilot reading AGENTS.md files, or "a single CLAUDE.md or GEMINI.md file stored in the root of the repository". Cline's supported-rule-types table detects .cursorrules and .windsurfrules automatically. Cursor lists AGENTS.md as a rule type beside its own. The practical arrangement is one canonical file of prose plus thin per-tool files that import or symlink it, which is also why the same repository shows up in this index under more than one format.
Does any of these formats publish a size limit?
Two of the five. Anthropic: "target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence." Cursor: "Keep rules under 500 lines", with the advice to split larger ones into composable rules. agents.md, GitHub's repository-instructions page and Cline's rules page publish no line count, byte budget or context-cost figure at all. That absence matters more than it looks: an instruction file is loaded into every request, so its length is a recurring cost rather than a one-off, and three of the five formats leave you to discover that for yourself.
How does RuleStack measure adoption?
By counting the files, not by reading the vendors. Every figure in the capability table above is a quotation from the vendor's own documentation with the date it was read; every figure in the adoption table below it is counted from real repositories in the RuleStack corpus and re-counted nightly. The two are kept apart deliberately, because they fail in different ways: a capability claim goes stale when a vendor ships, and an adoption count goes stale every night. Where a vendor's page does not carry a figure, the cell says "Not published" and names the page that was read, it is never an inference about what the vendor does not support.