The built-in agents-md plugin checks whether it is available through tengu_agents_md_mod, a switch controlled from Anthropic's servers. When that switch has no value, the check now falls back to true. The flag server has returned it as on for this site's account and for the anonymous baseline since 2026-09-18.
When active, the plugin loads a project's AGENTS.md file as project instructions. By default it does this only where the project has no CLAUDE.md. An instructionFiles option can instead:
- load
AGENTS.mdalongsideCLAUDE.md - leave
AGENTS.mdout - drop the project instructions
If a project has an AGENTS.md file and no CLAUDE.md, Claude may now follow the instructions in AGENTS.md. Whether that happens for a given account is decided by Anthropic's servers.
tengu_agents_md_mod On for this account, and not off by defaultThe flag server returned on for the one account this site reads, and nothing in this release compiles it off by default. The compiled default is shown below, and says which it is when we cannot read one: a fifth of gates compile in a string or a number rather than on or off, and most published releases have no gate table behind them at all. No client can see what the server returns for your account.
This account: on · anonymous baseline: on · compiled default in v2.1.281: on
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 v2.1.281. It isn't a statement about your account. What a flag value here can and cannot tell you
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.
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.
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.
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.
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.
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.
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.
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.