Unclear It is not clear what the five-class permission asks change in the prompts a user sees.
What
Artifacts are files and outputs Claude Code produces and can share. When working with artifacts, Claude Code sends a list of the capabilities it supports. In that list, the five_class_asks field used to be worked out at runtime. It is now the constant !0, which means it is always on.
- Before, the value came from the environment variable
CLAUDE_CODE_ARTIFACT_FIVE_CLASS_ASKS. An environment variable is a setting passed to a program from outside it. When that variable was not set, the value came from the remote flagtengu_cobalt_plinth_bryony, which defaulted to false. - The neighbouring capabilities
types_on,watch_railandauto_reactare still worked out at runtime. - Nobody checked whether the old helper is now unused or whether
CLAUDE_CODE_ARTIFACT_FIVE_CLASS_ASKSis still read anywhere.
Why
The capability no longer depends on a setting, so it is advertised for everyone. Setting CLAUDE_CODE_ARTIFACT_FIVE_CLASS_ASKS may no longer control it.
tengu_cobalt_plinth_bryony 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 v2.1.295: not a boolean we can read
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 v2.1.295. 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.
It is not clear what the five-class permission asks change in the prompts a user sees.