tengu_flint_harbor Running as an experimentThis flag is being run as an experiment, so a single reading is one arm of it and another account can be in another arm. Read the values below as a sample instead of a setting.
This account: off · anonymous baseline: on · compiled default in v2.1.94: 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.
tengu_flint_harbor_prompt Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.94: 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 v2.1.94. It isn't a statement about your account. What a flag value here can and cannot tell you
What's wrong with this entry?
Generates team onboarding guides by analysing your Claude Code usage patterns across sessions, then produces a shareable guide for teammates.
Feature-flagged via tengu_flint_harbor (default: false). Can also be enabled with CLAUDE_CODE_TEAM_ONBOARDING=1.
- Scans session transcripts for usage metrics: slash commands, MCP servers, project patterns
- Generates markdown onboarding guide with team-specific recommendations
- Uses allowed tools:
Edit(ONBOARDING.md)andBash(ls:*) - Shows progress: "scanning usage data"
- Discovery variant controlled by
tengu_cedar_inletflag - Custom prompt/template configurable via
tengu_flint_harbor_prompt - Onboarding banner visible to users: "On a team? Ask a teammate to run /team-onboarding and share the guide."
Command definition (search for "team-onboarding", "tengu_flint_harbor")
Strings lifted out of the shipped bundle, so the claim above can be checked against them.