What
- The setting is renamed from
projectInstructionstoinstructionFiles; the old name still works as a deprecated alias but logs a one-time warning telling you to migrate. - The recognized modes changed from
claude,agents-fallback,both,nonetoclaude-md,claude-md-or-agents-md,claude-md-and-agents-md,managed-only. - The default mode is now
claude-md-or-agents-md, so a project with no CLAUDE.md of its own now automatically gets its AGENTS.md files loaded instead, without needing to turn anything on. - New telemetry events (
agents_md_load,agents_md_nested) record file count, import count, total content length, and whether the file walk succeeded or failed, tagged by the resolved mode. - Project context-loading results now always include a
pluginInstructionFilesfield (withfileCountandtotalContentLength) alongside the existingclaudeMd,instructionFiles, andmemoryFilesfields.
Why
This clarifies and simplifies how Claude Code decides which project instruction files (CLAUDE.md, AGENTS.md) to load, makes AGENTS.md usable out of the box for projects that don't have their own CLAUDE.md, and gives better visibility into which instruction files, including ones contributed by plugins, actually got loaded.
Names in the bundleinstructionFilesAGENTS.md
Feature flag
tengu_agents_md_mod Off by default, switched on for this accountThe shipped code defaults this off, and the flag server returned on for the one account this site reads on this version. That is the reading that makes the entry above worth a second look, and it still says nothing about your account.
This account: on · anonymous baseline: on · compiled default in v2.1.277: off
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.277. It isn't a statement about your account. What a flag value here can and cannot tell you
Documented inclaude-code/memory
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on All settings touched a line naming instructionFiles after this was published.
Built-in plugins store their options under the same key with an `@builtin` suffix. For example, the [**Project instructions**](/docs/en/memory#choose-which-instruction-files-load) setting that controls whether Claude Code reads `AGENTS.md`…settings-reference see the edit
Added since
A small documentation edit on Glossary touched a line naming AGENTS.md after this was published.
A markdown file of project instructions you write for AI coding agents. If your repository has one and no [CLAUDE.md](#claude-md), Claude reads it as your project instructions without you adding a second file. You can change the **Project …glossary see the edit
Confirmed since
Anthropic's documentation has since written up AGENTS.md, on Explore the .claude directory.
| `AGENTS.md` | Project root, `.claude/`, or any directory | Project instructions you write for AI coding agents. Claude Code can [load it](/docs/en/memory#agents-md) on its own or alongside `CLAUDE.md`. |claude-directory see the edit
Flag reading moved
The flag server now returns on for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved
The flag server now returns off for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved
The flag server now returns on for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved
The flag server now returns off for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved
The flag server now returns on for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved
The flag server now returns off for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved
The flag server now returns on for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved
The flag server now returns off for tengu_agents_md_mod, read as this account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up AGENTS.md, on Explore the .claude directory.