Shopify’s CEO threatened to ban Claude Code. Anthropic had already closed the feature request.
Shopify CEO Tobi Lütke is considering banning Claude Code at the company, but not because he thinks Anthropic’s coding agent The post Shopify’s CEO threatened to ban Claude Code. Anthropic had already closed the feature request. appeared first on The New Stack .
Shopify's CEO Tobi Lütke is contemplating banning Claude Code at the company, not due to any dissatisfaction with Anthropic's coding agent, but because of a Markdown file. Lütke posted on X about his intention to ban Claude Code until they make changes to their file structure. Despite seeming like a minor disagreement, it could lead to bigger issues in a company as large as Shopify.
With thousands of developers working in a single monorepo, each using different AI coding tools, inconsistencies can arise. Lütke emphasized that while they have automated solutions, it is an unnecessary complexity tax for engineers.
Now, with more capable coding agents, engineering teams require methods to provide persistent instructions for codebases. This led to the creation of files like AGENTS.md and CLAUDE.md. Developers can include build commands, testing requirements, and coding conventions in these files, allowing agents to access the information without constant reminders. However, the problem arises when different coding tools do not follow the same convention.
OpenAI introduced AGENTS.md in August 2025, quickly adopted by over 60,000 open-source projects and agent frameworks. Anthropic's Claude Code, however, uses CLAUDE.md for project instructions and does not natively read AGENTS.md. Anthropic acknowledged developers' requests for support but closed the feature request as "not planned." Shopify, however, has already built automation to address this issue, acknowledging it as another job for platform teams as more coding agents are integrated into repositories.
Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Anthropic gives chat and Cowork one memory thenewstack.io
- Anthropic updates Claude’s memory to enhance customization and protect sensitive topics siliconangle.com
- Claude Cowork will now remember your conversations with chat androidauthority.com
- Claude Cowork finally remembers what you told the app in chat techcrunch.com
- Anthropic Unifies Memory Across Claude and Cowork cnet.com
- Anthropic update unifies memory feature across Claude Cowork and chat 9to5mac.com
- Anthropic merges the memory systems for Claude chat and Claude Cowork, making Claude chat history available to Cowork unless users opt out (David Gewirtz/ZDNET) zdnet.com