scan-domain-entities

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Prerequisites: MUST ATTENTION READ before executing:

Scan & Update Reference Doc — When updating reference docs: (1) Read existing doc first. (2) Scan codebase for current state (grep/glob). (3) Diff findings vs doc content. (4) Update ONLY sections where code diverged from doc. (5) Preserve manual annotations. (6) Update metadata (date, counts). NEVER rewrite entire doc — surgical updates only.

Output Quality — Reference docs are injected into AI context. Apply 10 rules: (1) No inventories/counts — AI can grep. (2) No directory trees — AI can glob. (3) No TOCs. (4) Rules > descriptions — "MUST ATTENTION use X" not "X allows you to...". (5) 1 example per pattern. (6) Tables > prose. (7) BAD/GOOD pairs: 2-3 lines each. (8) Primacy-recency anchoring — critical rules in first AND last 5 lines. (9) No checkbox checklists — bullets force reading. (10) Density target: >=8 MUST ATTENTION/NEVER/ALWAYS per 100 lines.

Quick Summary

Goal: Scan project codebase and populate docs/project-reference/domain-entities-reference.md with domain entities, data models, DTOs, aggregate boundaries, cross-service entity sync maps, and Mermaid ER diagrams. (content auto-injected by hook — check for [Injected: ...] header before reading)