init-deeplisted

# /init-deep Generate hierarchical AGENTS.md files. Root + complexity-scored subdirectories. ## Usage ``` /init-deep # Update mode: modify existing + create new where warranted /init-deep --create-new # Read existing → remove all → regenerate from scratch /init-deep --max-depth=2 # Limit directory depth (default: 3) ``` ## Workflow 1. **Discovery + Analysis** (concurrent) — explore agents + bash structure + codemap + existing AGENTS.md 2. **Score & Decide** — AGENTS.md locations from merged findings 3. **Generate** — root first, subdirs in parallel 4. **Review** — deduplicate, trim, validate Use TaskCreate for ALL phases. Mark in_progress → completed in real-time. ## Phase 1: Discovery + Analysis (Concurrent) ### Background Explore Agents (launch immediately) ``` Agent(subagent_type="oh-my-claudeagent:explore", prompt="Project structure: PREDICT standard patterns for detected language → REPORT deviations only") Agent(subagent_type="oh-my-claudeagent:explore", prompt="Entry points: FIND main files → REPORT non-standard organization") Agent(subagent_type="oh-my-claudeagent:explore", prompt="Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) → REPORT project-specific rules") Agent(subagent_type="oh-my-claudeagent:explore", prompt="Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments → LIST forbidden patterns") Agent(subagent_type="oh-my-claudeagent:explore", prompt="Build/CI: FIND .github/workf