Analyzes bounded contexts from the project's source tree, extracts domain knowledge per context, writes
ai-context/features/<context>.mdfiles, and producesteach-report.mdwith coverage metrics.
Triggers: /codebase-teach, teach codebase, extract domain knowledge, update feature docs, analyze bounded contexts
Claude execution wiring
These notes bind the tool-neutral logic above to the Claude Code harness. They are the EXECUTION layer that does not port to other tools.
- Feature template path — the neutral logic references the feature template
by its repo-relative path
skills/_templates/feature/_template.md. In the deployed Claude harness this resolves to the absolute~/.claude/skills/_templates/feature/_template.md(deployed from the agent-config repo). The skill MUST read it as the structural contract for the six-section feature file. - Project instruction file — the neutral "project instruction file" (Step 0,
Skills Registry extraction) is
CLAUDE.mdat the project root.