{"id":471518,"date":"2025-08-21T15:02:31","date_gmt":"2025-08-21T15:02:31","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=471518"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=471518","title":{"rendered":"<span>AGENTS.md: The README for Your AI Agent<\/span>"},"content":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<figure class=\"full-width\"><img decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/af9\/fbb\/ee0\/af9fbbee035eca88ad37971beb82a6c5.png\" alt=\"AGENTS.md: The README for Your AI Agent\" title=\"AGENTS.md: The README for Your AI Agent\" width=\"800\" height=\"435\" sizes=\"auto, (max-width: 780px) 100vw, 50vw\" srcset=\"https:\/\/habrastorage.org\/r\/w780\/getpro\/habr\/upload_files\/af9\/fbb\/ee0\/af9fbbee035eca88ad37971beb82a6c5.png 780w,&#10;       https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/af9\/fbb\/ee0\/af9fbbee035eca88ad37971beb82a6c5.png 781w\" loading=\"lazy\" decode=\"async\"\/><\/p>\n<div><figcaption><a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>: The README for Your AI Agent<\/figcaption><\/div>\n<\/figure>\n<p>If you\u2019re like me and work with multiple AI coding agents, you know the frustration of managing different instruction files. It\u2019s a pain to keep everything updated across various formats. But I\u2019ve got some great news for you. A new, simplified standard has emerged, and it\u2019s called <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>.<\/p>\n<h2>The Problem with Competing Standards<\/h2>\n<p>For a while now, working with different AI agents meant juggling multiple configuration files. Whether it was <a href=\"http:\/\/claude.md\" rel=\"noopener noreferrer nofollow\">claude.md<\/a>, <a href=\"http:\/\/gemini.md\" rel=\"noopener noreferrer nofollow\">gemini.md<\/a>, or .cursor\/rules, each agent had its own format. This created a mess of redundant files that all needed to be updated separately. It was inefficient and confusing.<\/p>\n<figure class=\"full-width\"><img decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/f5d\/d99\/7cf\/f5dd997cf339f4080d95deb25715fb79.png\" width=\"691\" height=\"1058\" sizes=\"auto, (max-width: 780px) 100vw, 50vw\" srcset=\"https:\/\/habrastorage.org\/r\/w780\/getpro\/habr\/upload_files\/f5d\/d99\/7cf\/f5dd997cf339f4080d95deb25715fb79.png 780w,&#10;       https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/f5d\/d99\/7cf\/f5dd997cf339f4080d95deb25715fb79.png 781w\" loading=\"lazy\" decode=\"async\"\/><\/figure>\n<p>Big companies recognized this problem. They came together to create a unified solution \u2014 <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>. The goal was to establish a single, predictable place for all AI agents to find the instructions they need to work on a project.<\/p>\n<h2>What is AGENTS.md?<\/h2>\n<p>Think of <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> as a README file, but for machines. It\u2019s a simple, open-source format that guides AI coding agents on how to interact with your project. It\u2019s already being used by over 20,000 open-source projects.<\/p>\n<p>This file provides all the necessary context for an AI to understand and work on your code, including:<\/p>\n<ul>\n<li>\n<p><strong>Setup Commands:<\/strong>\u00a0Instructions on how to install dependencies and build the project.<\/p>\n<\/li>\n<li>\n<p><strong>Code Style:<\/strong>\u00a0Rules on formatting and design patterns to ensure consistency.<\/p>\n<\/li>\n<li>\n<p><strong>Testing:<\/strong>\u00a0How to run tests to verify changes.<\/p>\n<\/li>\n<li>\n<p><strong>Commit Guidelines:<\/strong>\u00a0Preferred formats for commit messages and linting rules.<\/p>\n<\/li>\n<li>\n<p><strong>Custom Notes:<\/strong>\u00a0Any other important information, like security considerations or performance tips.<\/p>\n<\/li>\n<\/ul>\n<p>Look at the example below.<\/p>\n<pre><code># Sample AGENTS.md file## Dev environment tips- Use `pnpm dlx turbo run where &lt;project_name&gt;` to jump to a package instead of scanning with `ls`.- Run `pnpm install --filter &lt;project_name&gt;` to add the package to your workspace so Vite, ESLint, and TypeScript can see it.- Use `pnpm create vite@latest &lt;project_name&gt; -- --template react-ts` to spin up a new React + Vite package with TypeScript checks ready.- Check the name field inside each package's package.json to confirm the right name\u2014skip the top-level one.## Testing instructions- Find the CI plan in the .github\/workflows folder.- Run `pnpm turbo run test --filter &lt;project_name&gt;` to run every check defined for that package.- From the package root you can just call `pnpm test`. The commit should pass all tests before you merge.- To focus on one step, add the Vitest pattern: `pnpm vitest run -t \"&lt;test name&gt;\"`.- Fix any test or type errors until the whole suite is green.- After moving files or changing imports, run `pnpm lint --filter &lt;project_name&gt;` to be sure ESLint and TypeScript rules still pass.- Add or update tests for the code you change, even if nobody asked.## PR instructions- Title format: [&lt;project_name&gt;] &lt;Title&gt;- Always run `pnpm lint` and `pnpm test` before committing.<\/code><\/pre>\n<h2>How to Migrate to AGENTS.md<\/h2>\n<p>Migrating to <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> is straightforward. You can consolidate your existing instruction files in just two simple steps using your terminal:<\/p>\n<ol>\n<li>\n<p><strong>Rename your file:<\/strong>\u00a0Use the command\u00a0<strong><em>mv <\/em><\/strong><a href=\"http:\/\/AGENT.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENT.md<\/em><\/strong><\/a><strong><em> <\/em><\/strong><a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENTS.md<\/em><\/strong><\/a>\u00a0to rename your primary instruction file.<\/p>\n<\/li>\n<li>\n<p><strong>Create a symbolic link:<\/strong>\u00a0Use\u00a0<strong><em>ln -s <\/em><\/strong><a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENTS.md<\/em><\/strong><\/a><strong><em> <\/em><\/strong><a href=\"http:\/\/AGENT.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENT.md<\/em><\/strong><\/a>\u00a0to create a symbolic link. This ensures backward compatibility with any tools that haven\u2019t been updated to the new standard yet.<\/p>\n<\/li>\n<\/ol>\n<h2>How to Use AGENTS.md<\/h2>\n<p>Getting started with <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> is easy:<\/p>\n<ol>\n<li>\n<p><strong>Add the file:<\/strong>\u00a0Create an <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> file at the root of your repository.<\/p>\n<\/li>\n<li>\n<p><strong>Cover what matters:<\/strong>\u00a0Add sections for project overview, build and test commands, code style guidelines, and any other relevant instructions.<\/p>\n<\/li>\n<li>\n<p><strong>Add extra instructions:<\/strong>\u00a0Include commit messages, pull request guidelines, and anything else a new teammate would need to know.<\/p>\n<\/li>\n<\/ol>\n<h2>Best Practices<\/h2>\n<p>To get the most out of <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>, here are a few best practices to follow:<\/p>\n<ul>\n<li>\n<p><strong>Be explicit and concise:<\/strong>\u00a0Keep your instructions clear and to the point.<\/p>\n<\/li>\n<li>\n<p><strong>Keep instructions up to date:<\/strong>\u00a0Make sure the file is always current with your project\u2019s needs.<\/p>\n<\/li>\n<li>\n<p><strong>Link to existing docs:<\/strong>\u00a0Instead of duplicating information, link to your existing documentation.<\/p>\n<\/li>\n<li>\n<p><strong>Use multiple files for monorepos:<\/strong>\u00a0For large monorepos, you can use nested <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> files for different subprojects.<\/p>\n<\/li>\n<\/ul>\n<h2>Video Overview about Agents.MD<\/h2>\n<div class=\"tm-iframe_temp\" data-src=\"https:\/\/embedd.srv.habr.com\/iframe\/68a70fff6420910a65732d5c\" data-style=\"\" id=\"68a70fff6420910a65732d5c\" width=\"\"><\/div>\n<p><strong><em>Watch on YouTube: <\/em><\/strong><a href=\"http:\/\/agents.md\" rel=\"noopener noreferrer nofollow\"><strong><em>agents.md<\/em><\/strong><\/a><a href=\"https:\/\/youtu.be\/TC7dK0gwgg0?si=L2b4p%5C_CkoHLMDsI-\" rel=\"noopener noreferrer nofollow\"><strong><em> explained<\/em><\/strong><\/a><\/p>\n<p>And that\u2019s it! By adopting the <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> standard, you can streamline your workflow, ensure consistency, and make it easier for AI agents to work with your projects.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><!----><!----><\/div>\n<p><!----><!----><br \/> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/articles\/939420\/\"> https:\/\/habr.com\/ru\/articles\/939420\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<figure class=\"full-width\">\n<div><figcaption><a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>: The README for Your AI Agent<\/figcaption><\/div>\n<\/figure>\n<p>If you\u2019re like me and work with multiple AI coding agents, you know the frustration of managing different instruction files. It\u2019s a pain to keep everything updated across various formats. But I\u2019ve got some great news for you. A new, simplified standard has emerged, and it\u2019s called <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>.<\/p>\n<h2>The Problem with Competing Standards<\/h2>\n<p>For a while now, working with different AI agents meant juggling multiple configuration files. Whether it was <a href=\"http:\/\/claude.md\" rel=\"noopener noreferrer nofollow\">claude.md<\/a>, <a href=\"http:\/\/gemini.md\" rel=\"noopener noreferrer nofollow\">gemini.md<\/a>, or .cursor\/rules, each agent had its own format. This created a mess of redundant files that all needed to be updated separately. It was inefficient and confusing.<\/p>\n<figure class=\"full-width\"><\/figure>\n<p>Big companies recognized this problem. They came together to create a unified solution \u2014 <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>. The goal was to establish a single, predictable place for all AI agents to find the instructions they need to work on a project.<\/p>\n<h2>What is AGENTS.md?<\/h2>\n<p>Think of <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> as a README file, but for machines. It\u2019s a simple, open-source format that guides AI coding agents on how to interact with your project. It\u2019s already being used by over 20,000 open-source projects.<\/p>\n<p>This file provides all the necessary context for an AI to understand and work on your code, including:<\/p>\n<ul>\n<li>\n<p><strong>Setup Commands:<\/strong>\u00a0Instructions on how to install dependencies and build the project.<\/p>\n<\/li>\n<li>\n<p><strong>Code Style:<\/strong>\u00a0Rules on formatting and design patterns to ensure consistency.<\/p>\n<\/li>\n<li>\n<p><strong>Testing:<\/strong>\u00a0How to run tests to verify changes.<\/p>\n<\/li>\n<li>\n<p><strong>Commit Guidelines:<\/strong>\u00a0Preferred formats for commit messages and linting rules.<\/p>\n<\/li>\n<li>\n<p><strong>Custom Notes:<\/strong>\u00a0Any other important information, like security considerations or performance tips.<\/p>\n<\/li>\n<\/ul>\n<p>Look at the example below.<\/p>\n<pre><code># Sample AGENTS.md file## Dev environment tips- Use `pnpm dlx turbo run where &lt;project_name&gt;` to jump to a package instead of scanning with `ls`.- Run `pnpm install --filter &lt;project_name&gt;` to add the package to your workspace so Vite, ESLint, and TypeScript can see it.- Use `pnpm create vite@latest &lt;project_name&gt; -- --template react-ts` to spin up a new React + Vite package with TypeScript checks ready.- Check the name field inside each package's package.json to confirm the right name\u2014skip the top-level one.## Testing instructions- Find the CI plan in the .github\/workflows folder.- Run `pnpm turbo run test --filter &lt;project_name&gt;` to run every check defined for that package.- From the package root you can just call `pnpm test`. The commit should pass all tests before you merge.- To focus on one step, add the Vitest pattern: `pnpm vitest run -t \"&lt;test name&gt;\"`.- Fix any test or type errors until the whole suite is green.- After moving files or changing imports, run `pnpm lint --filter &lt;project_name&gt;` to be sure ESLint and TypeScript rules still pass.- Add or update tests for the code you change, even if nobody asked.## PR instructions- Title format: [&lt;project_name&gt;] &lt;Title&gt;- Always run `pnpm lint` and `pnpm test` before committing.<\/code><\/pre>\n<h2>How to Migrate to AGENTS.md<\/h2>\n<p>Migrating to <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> is straightforward. You can consolidate your existing instruction files in just two simple steps using your terminal:<\/p>\n<ol>\n<li>\n<p><strong>Rename your file:<\/strong>\u00a0Use the command\u00a0<strong><em>mv <\/em><\/strong><a href=\"http:\/\/AGENT.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENT.md<\/em><\/strong><\/a><strong><em> <\/em><\/strong><a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENTS.md<\/em><\/strong><\/a>\u00a0to rename your primary instruction file.<\/p>\n<\/li>\n<li>\n<p><strong>Create a symbolic link:<\/strong>\u00a0Use\u00a0<strong><em>ln -s <\/em><\/strong><a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENTS.md<\/em><\/strong><\/a><strong><em> <\/em><\/strong><a href=\"http:\/\/AGENT.md\" rel=\"noopener noreferrer nofollow\"><strong><em>AGENT.md<\/em><\/strong><\/a>\u00a0to create a symbolic link. This ensures backward compatibility with any tools that haven\u2019t been updated to the new standard yet.<\/p>\n<\/li>\n<\/ol>\n<h2>How to Use AGENTS.md<\/h2>\n<p>Getting started with <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> is easy:<\/p>\n<ol>\n<li>\n<p><strong>Add the file:<\/strong>\u00a0Create an <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> file at the root of your repository.<\/p>\n<\/li>\n<li>\n<p><strong>Cover what matters:<\/strong>\u00a0Add sections for project overview, build and test commands, code style guidelines, and any other relevant instructions.<\/p>\n<\/li>\n<li>\n<p><strong>Add extra instructions:<\/strong>\u00a0Include commit messages, pull request guidelines, and anything else a new teammate would need to know.<\/p>\n<\/li>\n<\/ol>\n<h2>Best Practices<\/h2>\n<p>To get the most out of <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a>, here are a few best practices to follow:<\/p>\n<ul>\n<li>\n<p><strong>Be explicit and concise:<\/strong>\u00a0Keep your instructions clear and to the point.<\/p>\n<\/li>\n<li>\n<p><strong>Keep instructions up to date:<\/strong>\u00a0Make sure the file is always current with your project\u2019s needs.<\/p>\n<\/li>\n<li>\n<p><strong>Link to existing docs:<\/strong>\u00a0Instead of duplicating information, link to your existing documentation.<\/p>\n<\/li>\n<li>\n<p><strong>Use multiple files for monorepos:<\/strong>\u00a0For large monorepos, you can use nested <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> files for different subprojects.<\/p>\n<\/li>\n<\/ul>\n<h2>Video Overview about Agents.MD<\/h2>\n<div class=\"tm-iframe_temp\" data-src=\"https:\/\/embedd.srv.habr.com\/iframe\/68a70fff6420910a65732d5c\" data-style=\"\" id=\"68a70fff6420910a65732d5c\" width=\"\"><\/div>\n<p><strong><em>Watch on YouTube: <\/em><\/strong><a href=\"http:\/\/agents.md\" rel=\"noopener noreferrer nofollow\"><strong><em>agents.md<\/em><\/strong><\/a><a href=\"https:\/\/youtu.be\/TC7dK0gwgg0?si=L2b4p%5C_CkoHLMDsI-\" rel=\"noopener noreferrer nofollow\"><strong><em> explained<\/em><\/strong><\/a><\/p>\n<p>And that\u2019s it! By adopting the <a href=\"http:\/\/AGENTS.md\" rel=\"noopener noreferrer nofollow\">AGENTS.md<\/a> standard, you can streamline your workflow, ensure consistency, and make it easier for AI agents to work with your projects.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><!----><!----><\/div>\n<p><!----><!----><br \/> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/articles\/939420\/\"> https:\/\/habr.com\/ru\/articles\/939420\/<\/a><br \/><\/br><\/br><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-471518","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/471518","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=471518"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/471518\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=471518"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=471518"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=471518"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}