ModelsSocial Commentary
Claude Code Now Reads AGENTS.md as Project Instructions
Support lands in version 2.1.277, built on Claude Code mods.
Claude Code version 2.1.277 adds AGENTS.md support. If no CLAUDE.md file exists in a folder, Claude now checks for and uses AGENTS.md instead. The fallback is automatic, requiring no extra configuration from the operator.
The feature is built on Claude Code mods, Anthropic's upcoming system for customizing the Claude Code harness. AGENTS.md support ships as a built-in mod, but operators will also be able to build custom versions of project instructions. Simon Willison's Weblog surfaced the announcement via a quote from Thariq Shihipar.
Watch the mods layer, not this single file format. If Claude Code mods become the standard way to ship project-level behavior, Anthropic controls the customization surface. Operators who rely on third-party agent frameworks using AGENTS.md now have a direct path in, but on Anthropic's infrastructure terms.
Analysis
The interesting part is who replied. Thibault Sottiaux of OpenAI answered "this is the way", which is a competitor endorsing a rival's move toward a shared standard, and the loudest pushback was that supporting AGENTS.md is bare-minimum rather than generous. Both readings point the same way: the file format is settling into a convention no single vendor owns, and the question underneath is Claude Code mods, the customisation layer this shipped on top of.
Research this with your AI
Copy the research prompt into your AI assistant to see how this story affects you.
Show the prompt
I just read this AI news story and want to understand it in my own context. Title: Claude Code Now Reads AGENTS.md as Project Instructions Summary: Anthropic's Claude Code now checks for AGENTS.md when no CLAUDE.md is present, starting in version 2.1.277. The feature is built on Claude Code mods, an upcoming customization layer for the tool's harness. Category: Models Source: X (@trq212), https://x.com/trq212/status/2101009392611278961 Using my own history and context, help me understand: 1. What is the core development and why does it matter? 2. Who are the major players involved and what are their motivations? 3. How does this fit into the broader AI landscape right now? 4. How does this apply to my own work, and what should I do or watch next? Be specific and plain spoken.
Newsletter
The day's AI stories, with the editor's take, in one email.
Free. Unsubscribe in one click.