feat(shared-skills): move init-deep to shared skill

assets/oh-my-opencode.schema.json

@@ -54,6 +54,7 @@
           "git-master",
           "review-work",
           "ai-slop-remover",
+          "init-deep",
           "team-mode"
         ]
       }
@@ -69,7 +70,6 @@
       "items": {
         "type": "string",
         "enum": [
-          "init-deep",
           "ralph-loop",
           "ulw-loop",
           "cancel-ralph",

packages/omo-codex/plugin/skills/init-deep/SKILL.md

@@ -0,0 +1,325 @@
+---
+name: init-deep
+description: "(builtin) Initialize hierarchical AGENTS.md knowledge base"
+---
+## Codex Harness Tool Compatibility
+
+This skill may include examples copied from the OpenCode harness. In Codex, do not call OpenCode-only tools such as `call_omo_agent(...)`, `task(...)`, `background_output(...)`, or `team_*(...)` literally. Translate those examples to Codex native tools:
+
+| OpenCode example | Codex tool to use |
+| --- | --- |
+| `call_omo_agent(subagent_type="explore", ...)` | `spawn_agent(agent_type="explorer", task_name="...", message="...")` |
+| `call_omo_agent(subagent_type="librarian", ...)` | `spawn_agent(agent_type="librarian", task_name="...", message="...")` |
+| `task(subagent_type="plan", ...)` | `spawn_agent(agent_type="plan", task_name="...", message="...")` |
+| `task(subagent_type="oracle", ...)` for final verification | `spawn_agent(agent_type="codex-ultrawork-reviewer", task_name="...", message="...")` |
+| `task(category="...", ...)` for implementation or QA | `spawn_agent(agent_type="worker", task_name="...", message="...")` |
+| `background_output(task_id="...")` | `wait_agent(...)` to wait for subagent completion and mailbox updates |
+| `team_*(...)` | Use Codex native subagents plus `send_message`, `followup_task`, `wait_agent`, and `close_agent` |
+
+When translating `load_skills=[...]`, include the requested skill names in the spawned agent's `message`. If a code block below conflicts with this section, this section wins.
+
+# /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 (High-Level)
+
+1. **Discovery + Analysis** (concurrent)
+   - Fire background explore agents immediately
+   - Main session: bash structure + LSP codemap + read existing AGENTS.md
+2. **Score & Decide** - Determine AGENTS.md locations from merged findings
+3. **Generate** - Root first, then subdirs in parallel
+4. **Review** - Deduplicate, trim, validate
+
+<critical>
+**TodoWrite ALL phases. Mark in_progress → completed in real-time.**
+```
+TodoWrite([
+  { id: "discovery", content: "Fire explore agents + LSP codemap + read existing", status: "pending", priority: "high" },
+  { id: "scoring", content: "Score directories, determine locations", status: "pending", priority: "high" },
+  { id: "generate", content: "Generate AGENTS.md files (root + subdirs)", status: "pending", priority: "high" },
+  { id: "review", content: "Deduplicate, validate, trim", status: "pending", priority: "medium" }
+])
+```
+</critical>
+
+---
+
+## Phase 1: Discovery + Analysis (Concurrent)
+
+**Mark "discovery" as in_progress.**
+
+### Fire Background Explore Agents IMMEDIATELY
+
+Don't wait-these run async while main session works.
+
+```
+// Fire all at once, collect results later
+task(subagent_type="explore", load_skills=[], description="Explore project structure", run_in_background=true, prompt="Project structure: PREDICT standard patterns for detected language → REPORT deviations only")
+task(subagent_type="explore", load_skills=[], description="Find entry points", run_in_background=true, prompt="Entry points: FIND main files → REPORT non-standard organization")
+task(subagent_type="explore", load_skills=[], description="Find conventions", run_in_background=true, prompt="Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) → REPORT project-specific rules")
+task(subagent_type="explore", load_skills=[], description="Find anti-patterns", run_in_background=true, prompt="Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments → LIST forbidden patterns")
+task(subagent_type="explore", load_skills=[], description="Explore build/CI", run_in_background=true, prompt="Build/CI: FIND .github/workflows, Makefile → REPORT non-standard patterns")
+task(subagent_type="explore", load_skills=[], description="Find test patterns", run_in_background=true, prompt="Test patterns: FIND test configs, test structure → REPORT unique conventions")
+```
+
+<dynamic-agents>
+**DYNAMIC AGENT SPAWNING**: After bash analysis, spawn ADDITIONAL explore agents based on project scale:
+
+| Factor | Threshold | Additional Agents |
+|--------|-----------|-------------------|
+| **Total files** | >100 | +1 per 100 files |
+| **Total lines** | >10k | +1 per 10k lines |
+| **Directory depth** | ≥4 | +2 for deep exploration |
+| **Large files (>500 lines)** | >10 files | +1 for complexity hotspots |
+| **Monorepo** | detected | +1 per package/workspace |
+| **Multiple languages** | >1 | +1 per language |
+
+```bash
+# Measure project scale first
+total_files=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)
+total_lines=$(find . -type f \\( -name "*.ts" -o -name "*.py" -o -name "*.go" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | tail -1 | awk '{print $1}')
+large_files=$(find . -type f \\( -name "*.ts" -o -name "*.py" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | awk '$1 > 500 {count++} END {print count+0}')
+max_depth=$(find . -type d -not -path '*/node_modules/*' -not -path '*/.git/*' | awk -F/ '{print NF}' | sort -rn | head -1)
+```
+
+Example spawning:
+```
+// 500 files, 50k lines, depth 6, 15 large files → spawn 5+5+2+1 = 13 additional agents
+task(subagent_type="explore", load_skills=[], description="Analyze large files", run_in_background=true, prompt="Large file analysis: FIND files >500 lines, REPORT complexity hotspots")
+task(subagent_type="explore", load_skills=[], description="Explore deep modules", run_in_background=true, prompt="Deep modules at depth 4+: FIND hidden patterns, internal conventions")
+task(subagent_type="explore", load_skills=[], description="Find shared utilities", run_in_background=true, prompt="Cross-cutting concerns: FIND shared utilities across directories")
+// ... more based on calculation
+```
+</dynamic-agents>
+
+### Main Session: Concurrent Analysis
+
+**While background agents run**, main session does:
+
+#### 1. Bash Structural Analysis
+```bash
+# Directory depth + file counts
+find . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c
+
+# Files per directory (top 30)
+find . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30
+
+# Code concentration by extension
+find . -type f \\( -name "*.py" -o -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.go" -o -name "*.rs" \\) -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20
+
+# Existing AGENTS.md / CLAUDE.md
+find . -type f \\( -name "AGENTS.md" -o -name "CLAUDE.md" \\) -not -path '*/node_modules/*' 2>/dev/null
+```
+
+#### 2. Read Existing AGENTS.md
+```
+For each existing file found:
+  Read(filePath=file)
+  Extract: key insights, conventions, anti-patterns
+  Store in EXISTING_AGENTS map
+```
+
+If `--create-new`: Read all existing first (preserve context) → then delete all → regenerate.
+
+#### 3. LSP Codemap (if available)
+```
+LspServers()  # Check availability
+
+# Entry points (parallel)
+LspDocumentSymbols(filePath="src/index.ts")
+LspDocumentSymbols(filePath="main.py")
+
+# Key symbols (parallel)
+LspWorkspaceSymbols(filePath=".", query="class")
+LspWorkspaceSymbols(filePath=".", query="interface")
+LspWorkspaceSymbols(filePath=".", query="function")
+
+# Centrality for top exports
+LspFindReferences(filePath="...", line=X, character=Y)
+```
+
+**LSP Fallback**: If unavailable, rely on explore agents + AST-grep.
+
+### Collect Background Results
+
+```
+// After main session analysis done, collect all task results
+for each background task ID (`bg_...`): background_output(task_id="bg_...")
+```
+
+**Merge: bash + LSP + existing + explore findings. Mark "discovery" as completed.**
+
+---
+
+## Phase 2: Scoring & Location Decision
+
+**Mark "scoring" as in_progress.**
+
+### Scoring Matrix
+
+| Factor | Weight | High Threshold | Source |
+|--------|--------|----------------|--------|
+| File count | 3x | >20 | bash |
+| Subdir count | 2x | >5 | bash |
+| Code ratio | 2x | >70% | bash |
+| Unique patterns | 1x | Has own config | explore |
+| Module boundary | 2x | Has index.ts/__init__.py | bash |
+| Symbol density | 2x | >30 symbols | LSP |
+| Export count | 2x | >10 exports | LSP |
+| Reference centrality | 3x | >20 refs | LSP |
+
+### Decision Rules
+
+| Score | Action |
+|-------|--------|
+| **Root (.)** | ALWAYS create |
+| **>15** | Create AGENTS.md |
+| **8-15** | Create if distinct domain |
+| **<8** | Skip (parent covers) |
+
+### Output
+```
+AGENTS_LOCATIONS = [
+  { path: ".", type: "root" },
+  { path: "src/hooks", score: 18, reason: "high complexity" },
+  { path: "src/api", score: 12, reason: "distinct domain" }
+]
+```
+
+**Mark "scoring" as completed.**
+
+---
+
+## Phase 3: Generate AGENTS.md
+
+**Mark "generate" as in_progress.**
+
+<critical>
+**File Writing Rule**: If AGENTS.md already exists at the target path → use `Edit` tool. If it does NOT exist → use `Write` tool.
+NEVER use Write to overwrite an existing file. ALWAYS check existence first via `Read` or discovery results.
+</critical>
+
+### Root AGENTS.md (Full Treatment)
+
+```markdown
+# PROJECT KNOWLEDGE BASE
+
+**Generated:** {TIMESTAMP}
+**Commit:** {SHORT_SHA}
+**Branch:** {BRANCH}
+
+## OVERVIEW
+{1-2 sentences: what + core stack}
+
+## STRUCTURE
+```
+{root}/
+├── {dir}/    # {non-obvious purpose only}
+└── {entry}
+```
+
+## WHERE TO LOOK
+| Task | Location | Notes |
+|------|----------|-------|
+
+## CODE MAP
+{From LSP - skip if unavailable or project <10 files}
+
+| Symbol | Type | Location | Refs | Role |
+|--------|------|----------|------|------|
+
+## CONVENTIONS
+{ONLY deviations from standard}
+
+## ANTI-PATTERNS (THIS PROJECT)
+{Explicitly forbidden here}
+
+## UNIQUE STYLES
+{Project-specific}
+
+## COMMANDS
+```bash
+{dev/test/build}
+```
+
+## NOTES
+{Gotchas}
+```
+
+**Quality gates**: 50-150 lines, no generic advice, no obvious info.
+
+### Subdirectory AGENTS.md (Parallel)
+
+Launch writing tasks for each location:
+
+```
+for loc in AGENTS_LOCATIONS (except root):
+  task(category="writing", load_skills=[], run_in_background=false, description="Generate AGENTS.md", prompt=`
+    Generate AGENTS.md for: ${loc.path}
+    - Reason: ${loc.reason}
+    - 30-80 lines max
+    - NEVER repeat parent content
+    - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS
+  `)
+```
+
+**Wait for all. Mark "generate" as completed.**
+
+---
+
+## Phase 4: Review & Deduplicate
+
+**Mark "review" as in_progress.**
+
+For each generated file:
+- Remove generic advice
+- Remove parent duplicates
+- Trim to size limits
+- Verify telegraphic style
+
+**Mark "review" as completed.**
+
+---
+
+## Final Report
+
+```
+=== init-deep Complete ===
+
+Mode: {update | create-new}
+
+Files:
+  [OK] ./AGENTS.md (root, {N} lines)
+  [OK] ./src/hooks/AGENTS.md ({N} lines)
+
+Dirs Analyzed: {N}
+AGENTS.md Created: {N}
+AGENTS.md Updated: {N}
+
+Hierarchy:
+  ./AGENTS.md
+  └── src/hooks/AGENTS.md
+```
+
+---
+
+## Anti-Patterns
+
+- **Static agent count**: MUST vary agents based on project size/depth
+- **Sequential execution**: MUST parallel (explore + LSP concurrent)
+- **Ignoring existing**: ALWAYS read existing first, even with --create-new
+- **Over-documenting**: Not every dir needs AGENTS.md
+- **Redundancy**: Child never repeats parent
+- **Generic content**: Remove anything that applies to ALL projects
+- **Verbose style**: Telegraphic or die

packages/omo-codex/plugin/test/sync-skills.test.mjs

@@ -11,6 +11,7 @@ const expectedSkills = [
 	"comment-checker",
 	"debugging",
 	"frontend-ui-ux",
+	"init-deep",
 	"lsp",
 	"metis",
 	"momus",

packages/shared-skills/skills/init-deep/SKILL.md

@@ -1,14 +1,18 @@
-export const INIT_DEEP_TEMPLATE = `# /init-deep
+---
+name: init-deep
+description: "(builtin) Initialize hierarchical AGENTS.md knowledge base"
+---
+# /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)
-\`\`\`
+```
 
 ---
 
@@ -23,14 +27,14 @@ Generate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.
 
 <critical>
 **TodoWrite ALL phases. Mark in_progress → completed in real-time.**
-\`\`\`
+```
 TodoWrite([
   { id: "discovery", content: "Fire explore agents + LSP codemap + read existing", status: "pending", priority: "high" },
   { id: "scoring", content: "Score directories, determine locations", status: "pending", priority: "high" },
   { id: "generate", content: "Generate AGENTS.md files (root + subdirs)", status: "pending", priority: "high" },
   { id: "review", content: "Deduplicate, validate, trim", status: "pending", priority: "medium" }
 ])
-\`\`\`
+```
 </critical>
 
 ---
@@ -43,7 +47,7 @@ TodoWrite([
 
 Don't wait-these run async while main session works.
 
-\`\`\`
+```
 // Fire all at once, collect results later
 task(subagent_type="explore", load_skills=[], description="Explore project structure", run_in_background=true, prompt="Project structure: PREDICT standard patterns for detected language → REPORT deviations only")
 task(subagent_type="explore", load_skills=[], description="Find entry points", run_in_background=true, prompt="Entry points: FIND main files → REPORT non-standard organization")
@@ -51,7 +55,7 @@ task(subagent_type="explore", load_skills=[], description="Find conventions", ru
 task(subagent_type="explore", load_skills=[], description="Find anti-patterns", run_in_background=true, prompt="Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments → LIST forbidden patterns")
 task(subagent_type="explore", load_skills=[], description="Explore build/CI", run_in_background=true, prompt="Build/CI: FIND .github/workflows, Makefile → REPORT non-standard patterns")
 task(subagent_type="explore", load_skills=[], description="Find test patterns", run_in_background=true, prompt="Test patterns: FIND test configs, test structure → REPORT unique conventions")
-\`\`\`
+```
 
 <dynamic-agents>
 **DYNAMIC AGENT SPAWNING**: After bash analysis, spawn ADDITIONAL explore agents based on project scale:
@@ -65,22 +69,22 @@ task(subagent_type="explore", load_skills=[], description="Find test patterns",
 | **Monorepo** | detected | +1 per package/workspace |
 | **Multiple languages** | >1 | +1 per language |
 
-\`\`\`bash
+```bash
 # Measure project scale first
 total_files=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)
 total_lines=$(find . -type f \\( -name "*.ts" -o -name "*.py" -o -name "*.go" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | tail -1 | awk '{print $1}')
 large_files=$(find . -type f \\( -name "*.ts" -o -name "*.py" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | awk '$1 > 500 {count++} END {print count+0}')
 max_depth=$(find . -type d -not -path '*/node_modules/*' -not -path '*/.git/*' | awk -F/ '{print NF}' | sort -rn | head -1)
-\`\`\`
+```
 
 Example spawning:
-\`\`\`
+```
 // 500 files, 50k lines, depth 6, 15 large files → spawn 5+5+2+1 = 13 additional agents
 task(subagent_type="explore", load_skills=[], description="Analyze large files", run_in_background=true, prompt="Large file analysis: FIND files >500 lines, REPORT complexity hotspots")
 task(subagent_type="explore", load_skills=[], description="Explore deep modules", run_in_background=true, prompt="Deep modules at depth 4+: FIND hidden patterns, internal conventions")
 task(subagent_type="explore", load_skills=[], description="Find shared utilities", run_in_background=true, prompt="Cross-cutting concerns: FIND shared utilities across directories")
 // ... more based on calculation
-\`\`\`
+```
 </dynamic-agents>
 
 ### Main Session: Concurrent Analysis
@@ -88,7 +92,7 @@ task(subagent_type="explore", load_skills=[], description="Find shared utilities
 **While background agents run**, main session does:
 
 #### 1. Bash Structural Analysis
-\`\`\`bash
+```bash
 # Directory depth + file counts
 find . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c
 
@@ -100,20 +104,20 @@ find . -type f \\( -name "*.py" -o -name "*.ts" -o -name "*.tsx" -o -name "*.js"
 
 # Existing AGENTS.md / CLAUDE.md
 find . -type f \\( -name "AGENTS.md" -o -name "CLAUDE.md" \\) -not -path '*/node_modules/*' 2>/dev/null
-\`\`\`
+```
 
 #### 2. Read Existing AGENTS.md
-\`\`\`
+```
 For each existing file found:
   Read(filePath=file)
   Extract: key insights, conventions, anti-patterns
   Store in EXISTING_AGENTS map
-\`\`\`
+```
 
-If \`--create-new\`: Read all existing first (preserve context) → then delete all → regenerate.
+If `--create-new`: Read all existing first (preserve context) → then delete all → regenerate.
 
 #### 3. LSP Codemap (if available)
-\`\`\`
+```
 LspServers()  # Check availability
 
 # Entry points (parallel)
@@ -127,16 +131,16 @@ LspWorkspaceSymbols(filePath=".", query="function")
 
 # Centrality for top exports
 LspFindReferences(filePath="...", line=X, character=Y)
-\`\`\`
+```
 
 **LSP Fallback**: If unavailable, rely on explore agents + AST-grep.
 
 ### Collect Background Results
 
-\`\`\`
+```
 // After main session analysis done, collect all task results
-for each background task ID (\`bg_...\`): background_output(task_id="bg_...")
+for each background task ID (`bg_...`): background_output(task_id="bg_...")
-\`\`\`
+```
 
 **Merge: bash + LSP + existing + explore findings. Mark "discovery" as completed.**
 
@@ -169,13 +173,13 @@ for each background task ID (\`bg_...\`): background_output(task_id="bg_...")
 | **<8** | Skip (parent covers) |
 
 ### Output
-\`\`\`
+```
 AGENTS_LOCATIONS = [
   { path: ".", type: "root" },
   { path: "src/hooks", score: 18, reason: "high complexity" },
   { path: "src/api", score: 12, reason: "distinct domain" }
 ]
-\`\`\`
+```
 
 **Mark "scoring" as completed.**
 
@@ -186,13 +190,13 @@ AGENTS_LOCATIONS = [
 **Mark "generate" as in_progress.**
 
 <critical>
-**File Writing Rule**: If AGENTS.md already exists at the target path → use \`Edit\` tool. If it does NOT exist → use \`Write\` tool.
+**File Writing Rule**: If AGENTS.md already exists at the target path → use `Edit` tool. If it does NOT exist → use `Write` tool.
-NEVER use Write to overwrite an existing file. ALWAYS check existence first via \`Read\` or discovery results.
+NEVER use Write to overwrite an existing file. ALWAYS check existence first via `Read` or discovery results.
 </critical>
 
 ### Root AGENTS.md (Full Treatment)
 
-\`\`\`markdown
+```markdown
 # PROJECT KNOWLEDGE BASE
 
 **Generated:** {TIMESTAMP}
@@ -203,11 +207,11 @@ NEVER use Write to overwrite an existing file. ALWAYS check existence first via
 {1-2 sentences: what + core stack}
 
 ## STRUCTURE
-\\\`\\\`\\\`
+```
 {root}/
 ├── {dir}/    # {non-obvious purpose only}
 └── {entry}
-\\\`\\\`\\\`
+```
 
 ## WHERE TO LOOK
 | Task | Location | Notes |
@@ -229,13 +233,13 @@ NEVER use Write to overwrite an existing file. ALWAYS check existence first via
 {Project-specific}
 
 ## COMMANDS
-\\\`\\\`\\\`bash
+```bash
 {dev/test/build}
-\\\`\\\`\\\`
+```
 
 ## NOTES
 {Gotchas}
-\`\`\`
+```
 
 **Quality gates**: 50-150 lines, no generic advice, no obvious info.
 
@@ -243,16 +247,16 @@ NEVER use Write to overwrite an existing file. ALWAYS check existence first via
 
 Launch writing tasks for each location:
 
-\`\`\`
+```
 for loc in AGENTS_LOCATIONS (except root):
-  task(category="writing", load_skills=[], run_in_background=false, description="Generate AGENTS.md", prompt=\\\`
+  task(category="writing", load_skills=[], run_in_background=false, description="Generate AGENTS.md", prompt=`
-    Generate AGENTS.md for: \${loc.path}
+    Generate AGENTS.md for: ${loc.path}
-    - Reason: \${loc.reason}
+    - Reason: ${loc.reason}
     - 30-80 lines max
     - NEVER repeat parent content
     - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS
-  \\\`)
+  `)
-\`\`\`
+```
 
 **Wait for all. Mark "generate" as completed.**
 
@@ -274,7 +278,7 @@ For each generated file:
 
 ## Final Report
 
-\`\`\`
+```
 === init-deep Complete ===
 
 Mode: {update | create-new}
@@ -290,7 +294,7 @@ AGENTS.md Updated: {N}
 Hierarchy:
   ./AGENTS.md
   └── src/hooks/AGENTS.md
-\`\`\`
+```
 
 ---
 
@@ -302,4 +306,4 @@ Hierarchy:
 - **Over-documenting**: Not every dir needs AGENTS.md
 - **Redundancy**: Child never repeats parent
 - **Generic content**: Remove anything that applies to ALL projects
-- **Verbose style**: Telegraphic or die`
+- **Verbose style**: Telegraphic or die

src/config/schema/agent-names.test.ts

@@ -1,11 +1,13 @@
+/// <reference path="../../../bun-test.d.ts" />
+
 import { describe, expect, test } from "bun:test"
 import { OhMyOpenCodeConfigSchema } from "./oh-my-opencode-config"
 
 describe("OhMyOpenCodeConfigSchema disabled_skills", () => {
-  test("accepts review-work and ai-slop-remover", () => {
+  test("accepts review-work, ai-slop-remover, and init-deep", () => {
     // given
     const config = {
-      disabled_skills: ["review-work", "ai-slop-remover"],
+      disabled_skills: ["review-work", "ai-slop-remover", "init-deep"],
     }
 
     // when
@@ -17,6 +19,7 @@ describe("OhMyOpenCodeConfigSchema disabled_skills", () => {
       expect(result.data.disabled_skills).toEqual([
         "review-work",
         "ai-slop-remover",
+        "init-deep",
       ])
     }
   })

src/config/schema/agent-names.ts

@@ -22,6 +22,7 @@ export const BuiltinSkillNameSchema = z.enum([
   "git-master",
   "review-work",
   "ai-slop-remover",
+  "init-deep",
   "team-mode",
 ])
 

src/config/schema/commands.ts

@@ -1,7 +1,6 @@
 import { z } from "zod"
 
 export const BuiltinCommandNameSchema = z.enum([
-  "init-deep",
   "ralph-loop",
   "ulw-loop",
   "cancel-ralph",

src/features/builtin-commands/commands.ts

@@ -1,7 +1,6 @@
 import type { CommandDefinition } from "../claude-code-command-loader"
 import { isAgentRegistered } from "../claude-code-session-state"
 import type { BuiltinCommandName, BuiltinCommands } from "./types"
-import { INIT_DEEP_TEMPLATE } from "./templates/init-deep"
 import { RALPH_LOOP_TEMPLATE, ULW_LOOP_TEMPLATE, CANCEL_RALPH_TEMPLATE } from "./templates/ralph-loop"
 import { STOP_CONTINUATION_TEMPLATE } from "./templates/stop-continuation"
 import { REFACTOR_TEMPLATE, REFACTOR_TEAM_MODE_ADDENDUM } from "./templates/refactor"
@@ -39,17 +38,6 @@ function createBuiltinCommandDefinitions(
   )
 
   return {
-    "init-deep": {
-      description: "(builtin) Initialize hierarchical AGENTS.md knowledge base",
-      template: `<command-instruction>
-${INIT_DEEP_TEMPLATE}
-</command-instruction>
-
-<user-request>
-$ARGUMENTS
-</user-request>`,
-      argumentHint: "[--create-new] [--max-depth=N]",
-    },
      "ralph-loop": {
        description: "(builtin) Start self-referential development loop until completion",
        template: `<command-instruction>

src/features/builtin-commands/init-deep-migration.test.ts

@@ -0,0 +1,16 @@
+/// <reference path="../../../bun-test.d.ts" />
+
+import { describe, expect, test } from "bun:test"
+import { loadBuiltinCommands } from "./commands"
+
+describe("init-deep skill migration", () => {
+	test("#given builtin commands #when loaded #then init-deep no longer ships as a command", () => {
+		// given
+
+		// when
+		const commands = loadBuiltinCommands()
+
+		// then
+		expect(commands["init-deep"]).toBeUndefined()
+	})
+})

src/features/builtin-commands/types.ts

@@ -1,6 +1,6 @@
 import type { CommandDefinition } from "../claude-code-command-loader"
 
-export type BuiltinCommandName = "init-deep" | "ralph-loop" | "cancel-ralph" | "ulw-loop" | "refactor" | "start-work" | "stop-continuation" | "handoff" | "remove-ai-slops" | "hyperplan"
+export type BuiltinCommandName = "ralph-loop" | "cancel-ralph" | "ulw-loop" | "refactor" | "start-work" | "stop-continuation" | "handoff" | "remove-ai-slops" | "hyperplan"
 
 export interface BuiltinCommandConfig {
   disabled_commands?: BuiltinCommandName[]

src/features/builtin-skills/shared-skill-extraction.test.ts

@@ -1,7 +1,13 @@
+/// <reference path="../../../bun-test.d.ts" />
+
 import { describe, expect, test } from "bun:test"
 import type { BuiltinSkill } from "./types"
 
-const TARGET_SKILLS = ["ai-slop-remover", "review-work", "frontend-ui-ux"] as const
+declare const Bun: {
+  file(path: string): { text(): Promise<string> }
+}
+
+const TARGET_SKILLS = ["ai-slop-remover", "review-work", "frontend-ui-ux", "init-deep"] as const
 
 type TargetSkill = (typeof TARGET_SKILLS)[number]
 
@@ -28,10 +34,13 @@ async function readSkillSource(name: TargetSkill): Promise<SkillSource> {
     case "review-work":
       skill = (await import("./skills/review-work")).reviewWorkSkill
       break
-    case "frontend-ui-ux":
+		case "frontend-ui-ux":
-      skill = (await import("./skills/frontend-ui-ux")).frontendUiUxSkill
+			skill = (await import("./skills/frontend-ui-ux")).frontendUiUxSkill
-      break
+			break
-  }
+		case "init-deep":
+			skill = (await import("./skills/init-deep")).initDeepSkill
+			break
+	}
   return { name, description: skill.description, template: skill.template }
 }
 

src/features/builtin-skills/skill-file-loader.test.ts

@@ -1,9 +1,15 @@
+/// <reference path="../../../bun-test.d.ts" />
+
 import { describe, expect, test } from "bun:test"
 import { parseFrontmatter } from "../../shared/frontmatter"
 import { createBuiltinSkills } from "./skills"
 import { createSharedSkillTemplateLoader, loadSharedSkillTemplate } from "./skill-file-loader"
 
-const SHARED_BUILTIN_SKILLS = ["ai-slop-remover", "review-work", "frontend-ui-ux"] as const
+declare const Bun: {
+  file(path: string): { text(): Promise<string> }
+}
+
+const SHARED_BUILTIN_SKILLS = ["ai-slop-remover", "review-work", "frontend-ui-ux", "init-deep"] as const
 
 describe("shared builtin skill file loader", () => {
   test("#given extracted shared skill files #when builtin skills are created #then templates load from SKILL.md bodies", async () => {

src/features/builtin-skills/skills.test.ts

@@ -1,3 +1,5 @@
+/// <reference path="../../../bun-test.d.ts" />
+
 import { describe, test, expect } from "bun:test"
 import { createBuiltinSkills } from "./skills"
 
@@ -83,7 +85,7 @@ describe("createBuiltinSkills", () => {
 		expect(agentBrowserSkill!.template).toContain("agent-browser snapshot")
 	})
 
-	test("always includes frontend-ui-ux, git-master, review-work, and ai-slop-remover skills", () => {
+	test("always includes frontend-ui-ux, git-master, review-work, ai-slop-remover, and init-deep skills", () => {
 		// given - both provider options
 
 		// when
@@ -97,10 +99,11 @@ describe("createBuiltinSkills", () => {
 			expect(skills.find((s) => s.name === "git-master")).toBeDefined()
 			expect(skills.find((s) => s.name === "review-work")).toBeDefined()
 			expect(skills.find((s) => s.name === "ai-slop-remover")).toBeDefined()
+			expect(skills.find((s) => s.name === "init-deep")).toBeDefined()
 		}
 	})
 
-	test("returns exactly 5 skills regardless of provider", () => {
+	test("returns exactly 6 skills regardless of provider", () => {
 		// given
 
 		// when
@@ -109,9 +112,9 @@ describe("createBuiltinSkills", () => {
 		const devBrowserSkills = createBuiltinSkills({ browserProvider: "dev-browser" })
 
 		// then
-		expect(defaultSkills).toHaveLength(5)
+		expect(defaultSkills).toHaveLength(6)
-		expect(agentBrowserSkills).toHaveLength(5)
+		expect(agentBrowserSkills).toHaveLength(6)
-		expect(devBrowserSkills).toHaveLength(5)
+		expect(devBrowserSkills).toHaveLength(6)
 	})
 
 	test("should exclude playwright when it is in disabledSkills", () => {
@@ -128,7 +131,8 @@ describe("createBuiltinSkills", () => {
 		expect(skills.map((s) => s.name)).not.toContain("dev-browser")
 		expect(skills.map((s) => s.name)).toContain("review-work")
 		expect(skills.map((s) => s.name)).toContain("ai-slop-remover")
-		expect(skills.length).toBe(4)
+		expect(skills.map((s) => s.name)).toContain("init-deep")
+		expect(skills.length).toBe(5)
 	})
 
 	test("should exclude multiple skills when they are in disabledSkills", () => {
@@ -145,12 +149,13 @@ describe("createBuiltinSkills", () => {
 		expect(skills.map((s) => s.name)).not.toContain("dev-browser")
 		expect(skills.map((s) => s.name)).toContain("review-work")
 		expect(skills.map((s) => s.name)).toContain("ai-slop-remover")
-		expect(skills.length).toBe(3)
+		expect(skills.map((s) => s.name)).toContain("init-deep")
+		expect(skills.length).toBe(4)
 	})
 
 	test("should return an empty array when all skills are disabled", () => {
 		// #given
-		const options = { disabledSkills: new Set(["playwright", "frontend-ui-ux", "git-master", "review-work", "ai-slop-remover"]) }
+		const options = { disabledSkills: new Set(["playwright", "frontend-ui-ux", "git-master", "review-work", "ai-slop-remover", "init-deep"]) }
 
 		// #when
 		const skills = createBuiltinSkills(options)
@@ -167,7 +172,22 @@ describe("createBuiltinSkills", () => {
 		const skills = createBuiltinSkills(options)
 
 		// #then
-		expect(skills.length).toBe(5)
+		expect(skills.length).toBe(6)
+	})
+
+	test("init-deep skill has correct structure", () => {
+		// #given - default options
+
+		// #when
+		const skills = createBuiltinSkills()
+		const initDeep = skills.find((s) => s.name === "init-deep")
+
+		// #then
+		expect(initDeep).toBeDefined()
+		expect(initDeep!.description).toContain("hierarchical AGENTS.md")
+		expect(initDeep!.argumentHint).toBe("[--create-new] [--max-depth=N]")
+		expect(initDeep!.template).toContain("Generate hierarchical AGENTS.md files")
+		expect(initDeep!.template).toContain("Discovery + Analysis")
 	})
 
 	test("review-work skill has correct structure", () => {

src/features/builtin-skills/skills.ts

@@ -8,6 +8,7 @@ import {
   frontendUiUxSkill,
   gitMasterSkill,
   devBrowserSkill,
+  initDeepSkill,
   reviewWorkSkill,
   aiSlopRemoverSkill,
   teamModeSkill,
@@ -33,7 +34,7 @@ export function createBuiltinSkills(options: CreateBuiltinSkillsOptions = {}): B
 		browserSkill = playwrightSkill
 	}
 
-	const skills = [browserSkill, frontendUiUxSkill, gitMasterSkill, reviewWorkSkill, aiSlopRemoverSkill]
+	const skills = [browserSkill, frontendUiUxSkill, gitMasterSkill, reviewWorkSkill, aiSlopRemoverSkill, initDeepSkill]
 
   if (teamModeEnabled && !disabledSkills?.has("team-mode")) {
     skills.push(teamModeSkill)

src/features/builtin-skills/skills/index.ts

@@ -5,4 +5,5 @@ export { gitMasterSkill } from "./git-master"
 export { devBrowserSkill } from "./dev-browser"
 export { reviewWorkSkill } from "./review-work"
 export { aiSlopRemoverSkill } from "./ai-slop-remover"
+export { initDeepSkill } from "./init-deep"
 export * from "./team-mode"

src/features/builtin-skills/skills/init-deep.ts

@@ -0,0 +1,9 @@
+import { loadSharedSkillTemplate } from "../skill-file-loader"
+import type { BuiltinSkill } from "../types"
+
+export const initDeepSkill: BuiltinSkill = {
+	name: "init-deep",
+	description: "(builtin) Initialize hierarchical AGENTS.md knowledge base",
+	template: loadSharedSkillTemplate("init-deep"),
+	argumentHint: "[--create-new] [--max-depth=N]",
+}

src/hooks/auto-slash-command/init-deep-skill.test.ts

@@ -0,0 +1,43 @@
+/// <reference path="../../../bun-test.d.ts" />
+
+import { describe, expect, test } from "bun:test"
+import { createBuiltinSkills } from "../../features/builtin-skills"
+import type { LoadedSkill } from "../../features/opencode-skill-loader"
+import { executeSlashCommand } from "./executor"
+
+function asLoadedSkill(name: string): LoadedSkill {
+	const skill = createBuiltinSkills().find((candidate) => candidate.name === name)
+	if (!skill) {
+		throw new Error(`missing builtin skill: ${name}`)
+	}
+
+	return {
+		name: skill.name,
+		definition: {
+			name: skill.name,
+			description: skill.description,
+			template: skill.template,
+			argumentHint: skill.argumentHint,
+		},
+		scope: "builtin",
+	}
+}
+
+describe("init-deep slash surface", () => {
+	test("#given init-deep builtin skill #when slash command executes #then it renders skill instructions with arguments", async () => {
+		// given
+		const skills = [asLoadedSkill("init-deep")]
+
+		// when
+		const result = await executeSlashCommand(
+			{ command: "init-deep", args: "--max-depth=2", raw: "/init-deep --max-depth=2" },
+			{ skills, pluginsEnabled: false },
+		)
+
+		// then
+		expect(result.success).toBe(true)
+		expect(result.replacementText).toContain("**Scope**: skill")
+		expect(result.replacementText).toContain("--max-depth=2")
+		expect(result.replacementText).toContain("Generate hierarchical AGENTS.md files")
+	})
+})