2026-08-25 15:39:17
\nShopify’s CEO threatened to ban Claude Code. Anthropic had already closed the feature request.<\/p>\n
Shopify CEO Tobi L\u00fctke is considering banning Claude Code at the company, but not because he thinks Anthropic\u2019s coding agent isn\u2019t good. The problem, he says, is a Markdown file<\/p>\n
\u201cI\u2019m thinking about banning Claude Code at Shopify until they change their mind and read AGENTS.md and .agents\/skills etc.,\u201d L\u00fctke posted Tuesday on X<\/p>\n
\n\u201cI\u2019m thinking about banning Claude Code at Shopify until they change their mind and read AGENTS.md and .agents\/skills etc.\u201d<\/p>\n<\/blockquote>\n
And while this might sound like a small disagreement over how an AI coding tool<\/a> is configured, at a company the size of Shopify, even a small difference can quickly become a much bigger issue<\/p>\n
Shopify has thousands of developers working in a massive monorepo, and because they don\u2019t all use the same AI coding tools, each agent needs to pick up the right instructions for whatever part of the codebase it happens to be working in. If one coding agent doesn\u2019t pick up the same instructions as the others, developers can end up with agents operating under different rules<\/p>\n
\u201cAgents and Claude files are recursively applied through the tree,\u201d L\u00fctke wrote in a follow-up post<\/a>. \u201cWith thousands of [developers] in a mono repo, it just does happen that one directory is missing one of the two files and this means that a subset of devs work with lobotomy.\u201d<\/p>\n
Shopify has built automation to work around the discrepancy, but L\u00fctke\u2019s core objection is that its engineers shouldn\u2019t have to<\/p>\n
\u201cWe fix this with automation, but it\u2019s a stupid complexity tax that shouldn\u2019t have to be paid,\u201d he writes<\/p>\n
\n\u201cWe fix this with automation, but it\u2019s a stupid complexity tax that shouldn\u2019t have to be paid.\u201d<\/p>\n<\/blockquote>\n
Now that coding agents are more capable, engineering teams have needed ways to provide persistent instructions for a codebase, which is where files such as AGENTS.md and CLAUDE.md come in<\/p>\n
Developers can put things like build commands, testing requirements, and coding conventions directly into a file in the repository, so the agent has that information as it works, rather than needing to be told every time. The problem is that coding tools haven\u2019t all standardized on the same convention<\/p>\n
OpenAI introduced AGENTS.md in August 2025 to give coding agents instructions specific to a project; by December, OpenAI said it was being used by more than 60,000 open-ding Codex, Cursor, Gemini CLI, GitHub Copilot, Jules and VS Code. OpenAI later handed the format over to the Agentic AI Foundation under the Linux Foundation<\/p>\n
\n\u201cAgents and Claude files are recursively applied through the tree\u2026 one directory is missing one of the two files and this means that a subset of devs work with lobotomy.\u201d<\/p>\n<\/blockquote>\n
Claude Code does things differently, however. It uses CLAUDE.md for project instructions and can pick up those files from different parts of a repository as it works. What it doesn\u2019t do is read AGENTS.md natively, something developers have been asking Anthropic to change<\/p>\n
Anthropic does provide workarounds, including importing AGENTS.md from a CLAUDE.md file or using symbolic links, but in a large repository, teams still have to make sure those instructions stay in sync across all the places they appear<\/p>\n
In a large codebase, those instructions can live throughout the directory tree, giving an agent different guidance depending on what it\u2019s working on. Claude Code does this with CLAUDE.md, picking up relevant instruction files as it moves through the repository<\/p>\n
That is also why L\u00fctke\u2019s example carries so much weight. If a directory contains instructions for tools reading AGENTS.md but the equivalent instructions aren\u2019t available to Claude Code, developers using Claude can end up working without the same context<\/p>\n
Developers have been asking Anthropic to support AGENTS.md for nearly a year.<\/a>. More recent requests have continued to push for native support, including one focused on recursive AGENTS.md discovery<\/a>, which Anthropic has closed as \u201cnot planned.\u201d<\/p>\n
And Shopify isn\u2019t alone. A 2026 study of 2,926 GitHub repositories found that context files are now the most common way developers give coding agents instructions, with AGENTS.md already being used across several different tools<\/p>\n
Shopify has already built automation to deal with the problem, a point L\u00fctke clearly made, stressing that as companies bring more coding agents into the same repositories, keeping those tools on the same page becomes one more job for platform teams<\/p>\n
TNS owner Insight Partners is an investor in: OpenAI, Anthropic.<\/p>\n
\n\n Related:<\/strong>
\n
\n Digital Automation Training Benin: 5 Winning Skills Employers Demand in 2026
\n <\/a>\n <\/p>\n\n <a href="https:\/\/yoursite.com\/automation-africa\/" title="WhatsApp<\/a> Marketing Automation<\/a> Africa: 6 Dangerous Mistakes Brands Make in Nigeria”>
\n WhatsApp Marketing Automation Africa: 6 Dangerous Mistakes Brands Make in Nigeria
\n <\/a>\n <\/p>\n<\/div>\n\nWant to learn this practically?<\/h3>\n
Join Justfine Infotech<\/strong> and build real digital skills in AI, automation, web development, digital marketing, office productivity, e-commerce, freelancing and cybersecurity.<\/p>\n
Available Programmes:<\/strong>
\n 6 Weeks Certificate \u2022 3 Months Professional Certificate \u2022 6 Months Diploma \u2022 Full Professional Diploma<\/p>\nWhatsApp:<\/strong>
\n +229 01 57 57 99 15
\n +229 01 66 68 11 60<\/p>\n