An alternate opening line for Claude's system prompt can be switched on with an environment variable.
The reworded intro sits behind CLAUDE_CODE_INTRO_FRAME or a server flag that falls back to off.
tengu_ochre_wren Off in both readingsThe flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.
This account: off · anonymous baseline: off · compiled default in v2.1.239: on
Read once, for one account on one subscription tier, against v2.1.239. It isn't a statement about your account. What a flag value here can and cannot tell you
What's wrong with this entry?
An experiment replaces the system prompt's opening line, in both the standard and the lean variant, with "You are an agent working with the user toward their goals, using your own judgment along the way." in place of "You are an interactive agent that helps users with software engineering tasks." It is controlled by the CLAUDE_CODE_INTRO_FRAME environment variable, and otherwise by a server-side flag named tengu_ochre_wren that falls back to off.
- The result is cached for the process and logged as
intro_frame_arm_active source=with eitherenvorgrowthbook, so you can tell which decided it. - Both the flag and the new sentence are absent from v2.1.238.
You are an agent working with the user toward their goals, using your own judgment along the way.
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.219
Opus 5 gets an extra system-prompt instruction restricting AgentTool, workflows and deep-research
Both mention system prompt
-
v2.1.219
Opus 5 carries an extra system-prompt block and suppresses subagent nudges
Both mention system prompt
-
v2.1.229
Bash tool prompt always carries the full git commit instructions
Both mention system prompt