Deep codebase initialization. Two outputs: (1) hierarchical CLAUDE.md files for human navigation; (2) a machine-readable context_brief.md that other skills (brainstorming, greenfield-scaffold, input-classifier) can load directly as structured context. TRIGGER when initializing a new repo, onboarding an agent to an unfamiliar codebase, or when input-classifier needs codebase context and no context_brief.md exists.
$npx -y skills add listener-he/java-harness-agent --skill deepinitInstalls into the current project.
Run `npx skills use "https://github.com/listener-he/java-harness-agent" --skill "listener-he/java-harness-agent/deepinit"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/listener-he/java-harness-agent" that are relevant to the current task. Run `npx skills add "https://github.com/listener-he/java-harness-agent"` and select the relevant skills, then follow their instructions.