tengu_vellum_lantern 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 v2.1.120: no gate table built for this version
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 v2.1.120. It isn't a statement about your account. What a flag value here can and cannot tell you
What's wrong with this entry?
A new prompt optimization mode that significantly reduces system prompt token usage by sending shorter, denser tool descriptions to capable models.
CLAUDE_CODE_LEAN_PROMPT=1 claude # force enable via env var- When active, tool descriptions for Grep, Glob, WebFetch, Write, Edit, WebSearch, TodoWrite, Bash, and the Task/Explore agent are replaced with much shorter versions
- Example: the Grep tool description goes from a multi-paragraph usage guide to a compact 4-line summary
- The Explore agent description is refined to emphasize it is a "read-only search agent" not suitable for code review or cross-file analysis
- Activated by the
CLAUDE_CODE_LEAN_PROMPTenvironment variable, or gradually rolled out via thetengu_vellum_lanternfeature flag - Currently limited to Opus 4.6+ and Opus 4.7 models
Lean prompt gate function checks CLAUDE_CODE_LEAN_PROMPT and tengu_vellum_lantern — search for "CLAUDE_CODE_LEAN_PROMPT"
Strings lifted out of the shipped bundle, so the claim above can be checked against them.