diff --git a/AGENTS.md b/AGENTS.md
index 0423ea5..c419669 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,7 +1,7 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2025-12-22T02:23:00+09:00
-**Commit:** aad7a72
+**Generated:** 2025-12-24T17:07:00+09:00
+**Commit:** 0172241
 **Branch:** dev
 
 ## OVERVIEW
@@ -13,14 +13,14 @@ OpenCode plugin implementing Claude Code/AmpCode features. Multi-model agent orc
 ```
 oh-my-opencode/
 ├── src/
-│   ├── agents/        # AI agents (Sisyphus, oracle, librarian, explore, frontend, document-writer, multimodal-looker)
-│   ├── hooks/         # 21 lifecycle hooks (comment-checker, rules-injector, keyword-detector, etc.)
-│   ├── tools/         # LSP (11), AST-Grep, Grep, Glob, background-task, look-at, skill, slashcommand, interactive-bash, call-omo-agent
-│   ├── mcp/           # MCP servers (context7, websearch_exa, grep_app)
-│   ├── features/      # Background agent, Claude Code loaders (agent, command, skill, mcp, session-state), hook-message-injector
+│   ├── agents/        # AI agents (7): Sisyphus, oracle, librarian, explore, frontend, document-writer, multimodal-looker
+│   ├── hooks/         # 21 lifecycle hooks - see src/hooks/AGENTS.md
+│   ├── tools/         # LSP, AST-Grep, Grep, Glob, etc. - see src/tools/AGENTS.md
+│   ├── mcp/           # MCP servers: context7, websearch_exa, grep_app
+│   ├── features/      # Claude Code compatibility - see src/features/AGENTS.md
 │   ├── config/        # Zod schema, TypeScript types
-│   ├── auth/          # Google Antigravity OAuth
-│   ├── shared/        # Utilities (deep-merge, pattern-matcher, logger, etc.)
+│   ├── auth/          # Google Antigravity OAuth (antigravity/)
+│   ├── shared/        # Utilities: deep-merge, pattern-matcher, logger, etc.
 │   └── index.ts       # Main plugin entry (OhMyOpenCodePlugin)
 ├── script/            # build-schema.ts, publish.ts, generate-changelog.ts
 ├── assets/            # JSON schema
@@ -31,12 +31,12 @@ oh-my-opencode/
 
 | Task | Location | Notes |
 |------|----------|-------|
-| Add new agent | `src/agents/` | Create .ts file, add to builtinAgents in index.ts, update types.ts |
-| Add new hook | `src/hooks/` | Create dir with createXXXHook(), export from index.ts |
-| Add new tool | `src/tools/` | Dir with index/types/constants/tools.ts, add to builtinTools |
-| Add MCP server | `src/mcp/` | Create config, add to index.ts |
-| Modify LSP behavior | `src/tools/lsp/` | client.ts for connection, tools.ts for handlers |
-| AST-Grep patterns | `src/tools/ast-grep/` | napi.ts for @ast-grep/napi binding |
+| Add agent | `src/agents/` | Create .ts, add to builtinAgents in index.ts, update types.ts |
+| Add hook | `src/hooks/` | Create dir with createXXXHook(), export from index.ts |
+| Add tool | `src/tools/` | Dir with index/types/constants/tools.ts, add to builtinTools |
+| Add MCP | `src/mcp/` | Create config, add to index.ts |
+| LSP behavior | `src/tools/lsp/` | client.ts (connection), tools.ts (handlers) |
+| AST-Grep | `src/tools/ast-grep/` | napi.ts for @ast-grep/napi binding |
 | Google OAuth | `src/auth/antigravity/` | OAuth plugin for Google models |
 | Config schema | `src/config/schema.ts` | Zod schema, run `bun run build:schema` after changes |
 | Claude Code compat | `src/features/claude-code-*-loader/` | Command, skill, agent, mcp loaders |
@@ -50,98 +50,72 @@ oh-my-opencode/
 - **Build**: Dual output - `bun build` (ESM) + `tsc --emitDeclarationOnly`
 - **Exports**: Barrel pattern - `export * from "./module"` in index.ts
 - **Directory naming**: kebab-case (`ast-grep/`, `claude-code-hooks/`)
-- **Tool structure**: Each tool has index.ts, types.ts, constants.ts, tools.ts, utils.ts
+- **Tool structure**: index.ts, types.ts, constants.ts, tools.ts, utils.ts
 - **Hook pattern**: `createXXXHook(input: PluginInput)` returning event handlers
-- **Test style**: BDD comments `#given`, `#when`, `#then` (same as AAA pattern)
+- **Test style**: BDD comments `#given`, `#when`, `#then` (same as AAA)
 
 ## ANTI-PATTERNS (THIS PROJECT)
 
 - **npm/yarn**: Use bun exclusively
 - **@types/node**: Use bun-types
-- **Bash file operations**: Never use mkdir/touch/rm/cp/mv for file creation in code
-- **Generic AI aesthetics**: No Space Grotesk, avoid typical AI-generated UI patterns
-- **Direct bun publish**: Use GitHub Actions workflow_dispatch only (OIDC provenance)
-- **Local version bump**: Version managed by CI workflow, never modify locally
+- **Bash file ops**: Never mkdir/touch/rm/cp/mv for file creation in code
+- **Direct bun publish**: GitHub Actions workflow_dispatch only (OIDC provenance)
+- **Local version bump**: Version managed by CI workflow
+- **Year 2024**: NEVER use 2024 in code/prompts (use current year)
 - **Rush completion**: Never mark tasks complete without verification
-- **Interrupting work**: Complete tasks fully before stopping
 - **Over-exploration**: Stop searching when sufficient context found
 
 ## UNIQUE STYLES
 
-- **Platform handling**: Union type `"darwin" | "linux" | "win32" | "unsupported"`
-- **Optional props**: Extensive use of `?` for optional interface properties
+- **Platform**: Union type `"darwin" | "linux" | "win32" | "unsupported"`
+- **Optional props**: Extensive `?` for optional interface properties
 - **Flexible objects**: `Record<string, unknown>` for dynamic configs
-- **Error handling**: Consistent try/catch with async/await in all tools
-- **Agent tools restriction**: Use `tools: { include: [...] }` or `tools: { exclude: [...] }`
+- **Error handling**: Consistent try/catch with async/await
+- **Agent tools**: `tools: { include: [...] }` or `tools: { exclude: [...] }`
 - **Temperature**: Most agents use `0.1` for consistency
-- **Hook naming**: `createXXXHook` function naming convention
-- **Date references**: NEVER use 2024 in code/prompts (use current year)
+- **Hook naming**: `createXXXHook` function convention
 
 ## AGENT MODELS
 
 | Agent | Model | Purpose |
 |-------|-------|---------|
-| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator, team leader |
-| oracle | openai/gpt-5.2 | Strategic advisor, code review, architecture |
-| librarian | anthropic/claude-sonnet-4-5 | Multi-repo analysis, docs lookup, GitHub examples |
-| explore | opencode/grok-code | Fast codebase exploration, file patterns |
-| frontend-ui-ux-engineer | google/gemini-3-pro-preview | UI generation, design-focused |
-| document-writer | google/gemini-3-pro-preview | Technical documentation |
-| multimodal-looker | google/gemini-3-flash | PDF/image/diagram analysis |
+| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator |
+| oracle | openai/gpt-5.2 | Strategic advisor, code review |
+| librarian | anthropic/claude-sonnet-4-5 | Multi-repo analysis, docs |
+| explore | opencode/grok-code | Fast codebase exploration |
+| frontend-ui-ux-engineer | google/gemini-3-pro-preview | UI generation |
+| document-writer | google/gemini-3-pro-preview | Technical docs |
+| multimodal-looker | google/gemini-3-flash | PDF/image analysis |
 
 ## COMMANDS
 
 ```bash
-# Type check
-bun run typecheck
-
-# Build (ESM + declarations + schema)
-bun run build
-
-# Clean + Build
-bun run rebuild
-
-# Build schema only
-bun run build:schema
-
-# Run tests
-bun test
+bun run typecheck      # Type check
+bun run build          # ESM + declarations + schema
+bun run rebuild        # Clean + Build
+bun run build:schema   # Schema only
+bun test               # Run tests
 ```
 
 ## DEPLOYMENT
 
 **GitHub Actions workflow_dispatch only**
 
-1. package.json version NOT modified locally (auto-bumped by workflow)
+1. Never modify package.json version locally
 2. Commit & push changes
-3. Trigger `publish` workflow manually:
-   - `bump`: major | minor | patch
-   - `version`: (optional) specific version override
+3. Trigger `publish` workflow: `gh workflow run publish -f bump=patch`
 
-```bash
-# Trigger via CLI
-gh workflow run publish -f bump=patch
-
-# Check status
-gh run list --workflow=publish
-```
-
-**Critical**:
-- Never run `bun publish` directly (OIDC provenance issue)
-- Never bump version locally
+**Critical**: Never `bun publish` directly. Never bump version locally.
 
 ## CI PIPELINE
 
-- **ci.yml**: Parallel test/typecheck jobs, build verification, auto-commit schema changes on master
-- **publish.yml**: Manual workflow_dispatch, version bump, changelog generation, OIDC npm publishing
-- Schema auto-commit prevents build drift
-- Draft release creation on dev branch
+- **ci.yml**: Parallel test/typecheck, build verification, auto-commit schema on master
+- **publish.yml**: Manual workflow_dispatch, version bump, changelog, OIDC npm publish
 
 ## NOTES
 
-- **Testing**: Bun native test framework (`bun test`), BDD-style with `#given/#when/#then` comments
-- **OpenCode version**: Requires >= 1.0.150 (earlier versions have config bugs)
-- **Multi-language docs**: README.md (EN), README.ko.md (KO), README.ja.md (JA), README.zh-cn.md (ZH-CN)
-- **Config locations**: `~/.config/opencode/oh-my-opencode.json` (user) or `.opencode/oh-my-opencode.json` (project)
-- **Schema autocomplete**: Add `$schema` field in config for IDE support
-- **Trusted dependencies**: @ast-grep/cli, @ast-grep/napi, @code-yeongyu/comment-checker
+- **Testing**: Bun native test (`bun test`), BDD-style `#given/#when/#then`
+- **OpenCode**: Requires >= 1.0.150
+- **Multi-lang docs**: README.md (EN), README.ko.md (KO), README.ja.md (JA), README.zh-cn.md (ZH-CN)
+- **Config**: `~/.config/opencode/oh-my-opencode.json` (user) or `.opencode/oh-my-opencode.json` (project)
+- **Trusted deps**: @ast-grep/cli, @ast-grep/napi, @code-yeongyu/comment-checker
diff --git a/src/features/AGENTS.md b/src/features/AGENTS.md
new file mode 100644
index 0000000..0a8d8f7
--- /dev/null
+++ b/src/features/AGENTS.md
@@ -0,0 +1,78 @@
+# FEATURES KNOWLEDGE BASE
+
+## OVERVIEW
+
+Claude Code compatibility layer and core feature modules. Enables Claude Code configs/commands/skills/MCPs/hooks to work seamlessly in OpenCode.
+
+## STRUCTURE
+
+```
+features/
+├── background-agent/           # Background task management
+│   ├── manager.ts              # Task lifecycle, notifications
+│   ├── manager.test.ts
+│   └── types.ts
+├── claude-code-agent-loader/   # Load agents from ~/.claude/agents/*.md
+├── claude-code-command-loader/ # Load commands from ~/.claude/commands/*.md
+├── claude-code-mcp-loader/     # Load MCPs from .mcp.json
+│   └── env-expander.ts         # ${VAR} expansion
+├── claude-code-session-state/  # Session state persistence
+├── claude-code-skill-loader/   # Load skills from ~/.claude/skills/*/SKILL.md
+└── hook-message-injector/      # Inject messages into conversation
+```
+
+## LOADER PRIORITY
+
+Each loader reads from multiple directories (highest priority first):
+
+| Loader | Priority Order |
+|--------|---------------|
+| Commands | `.opencode/command/` > `~/.config/opencode/command/` > `.claude/commands/` > `~/.claude/commands/` |
+| Skills | `.claude/skills/` > `~/.claude/skills/` |
+| Agents | `.claude/agents/` > `~/.claude/agents/` |
+| MCPs | `.claude/.mcp.json` > `.mcp.json` > `~/.claude/.mcp.json` |
+
+## HOW TO ADD A LOADER
+
+1. Create directory: `src/features/claude-code-my-loader/`
+2. Create files:
+   - `loader.ts`: Main loader logic with `load()` function
+   - `types.ts`: TypeScript interfaces
+   - `index.ts`: Barrel export
+3. Pattern: Read from multiple dirs, merge with priority, return normalized config
+
+## BACKGROUND AGENT SPECIFICS
+
+- **Task lifecycle**: pending → running → completed/failed
+- **Notifications**: OS notification on task complete (configurable)
+- **Result retrieval**: `background_output` tool with task_id
+- **Cancellation**: `background_cancel` with task_id or all=true
+
+## CONFIG TOGGLES
+
+Disable features in `oh-my-opencode.json`:
+
+```json
+{
+  "claude_code": {
+    "mcp": false,      // Skip .mcp.json loading
+    "commands": false, // Skip commands/*.md loading
+    "skills": false,   // Skip skills/*/SKILL.md loading
+    "agents": false,   // Skip agents/*.md loading
+    "hooks": false     // Skip settings.json hooks
+  }
+}
+```
+
+## HOOK MESSAGE INJECTOR
+
+- **Purpose**: Inject system messages into conversation at specific points
+- **Timing**: PreToolUse, PostToolUse, UserPromptSubmit, Stop
+- **Format**: Returns `{ messages: [{ role: "user", content: "..." }] }`
+
+## ANTI-PATTERNS (FEATURES)
+
+- **Blocking on load**: Loaders run at startup, keep them fast
+- **No error handling**: Always try/catch, log failures, return empty on error
+- **Ignoring priority**: Higher priority dirs must override lower
+- **Modifying user files**: Loaders read-only, never write to ~/.claude/
diff --git a/src/hooks/AGENTS.md b/src/hooks/AGENTS.md
new file mode 100644
index 0000000..36abe0f
--- /dev/null
+++ b/src/hooks/AGENTS.md
@@ -0,0 +1,83 @@
+# HOOKS KNOWLEDGE BASE
+
+## OVERVIEW
+
+Lifecycle hooks that intercept/modify agent behavior. Inject context, enforce rules, recover from errors, notify on events.
+
+## STRUCTURE
+
+```
+hooks/
+├── agent-usage-reminder/       # Remind to use specialized agents
+├── anthropic-auto-compact/     # Auto-compact Claude at token limit
+├── auto-update-checker/        # Version update notifications
+├── background-notification/    # OS notify on background task complete
+├── claude-code-hooks/          # Claude Code settings.json integration
+├── comment-checker/            # Prevent excessive AI comments
+│   ├── filters/                # Filtering rules (docstring, directive, bdd, etc.)
+│   └── output/                 # Output formatting
+├── compaction-context-injector/ # Inject context during compaction
+├── directory-agents-injector/  # Auto-inject AGENTS.md files
+├── directory-readme-injector/  # Auto-inject README.md files
+├── empty-message-sanitizer/    # Sanitize empty messages
+├── interactive-bash-session/   # Tmux session management
+├── keyword-detector/           # Detect ultrawork/search keywords
+├── non-interactive-env/        # CI/headless environment handling
+├── preemptive-compaction/      # Pre-emptive session compaction
+├── rules-injector/             # Conditional rules from .claude/rules/
+├── session-recovery/           # Recover from session errors
+├── think-mode/                 # Auto-detect thinking triggers
+├── context-window-monitor.ts   # Monitor context usage (standalone)
+├── empty-task-response-detector.ts
+├── session-notification.ts     # OS notify on idle (standalone)
+├── todo-continuation-enforcer.ts # Force TODO completion (standalone)
+└── tool-output-truncator.ts    # Truncate verbose outputs (standalone)
+```
+
+## HOOK CATEGORIES
+
+| Category | Hooks | Purpose |
+|----------|-------|---------|
+| Context Injection | directory-agents-injector, directory-readme-injector, rules-injector, compaction-context-injector | Auto-inject relevant context |
+| Session Management | session-recovery, anthropic-auto-compact, preemptive-compaction, empty-message-sanitizer | Handle session lifecycle |
+| Output Control | comment-checker, tool-output-truncator | Control agent output quality |
+| Notifications | session-notification, background-notification, auto-update-checker | OS/user notifications |
+| Behavior Enforcement | todo-continuation-enforcer, keyword-detector, think-mode, agent-usage-reminder | Enforce agent behavior |
+| Environment | non-interactive-env, interactive-bash-session, context-window-monitor | Adapt to runtime environment |
+| Compatibility | claude-code-hooks | Claude Code settings.json support |
+
+## HOW TO ADD A HOOK
+
+1. Create directory: `src/hooks/my-hook/`
+2. Create files:
+   - `index.ts`: Export `createMyHook(input: PluginInput)`
+   - `constants.ts`: Hook name constant
+   - `types.ts`: TypeScript interfaces (optional)
+   - `storage.ts`: Persistent state (optional)
+3. Return event handlers: `{ PreToolUse?, PostToolUse?, UserPromptSubmit?, Stop?, onSummarize? }`
+4. Export from `src/hooks/index.ts`
+5. Register in main plugin
+
+## HOOK EVENTS
+
+| Event | Timing | Can Block | Use Case |
+|-------|--------|-----------|----------|
+| PreToolUse | Before tool exec | Yes | Validate, modify input |
+| PostToolUse | After tool exec | No | Add context, warnings |
+| UserPromptSubmit | On user prompt | Yes | Inject messages, block |
+| Stop | Session idle | No | Inject follow-ups |
+| onSummarize | During compaction | No | Preserve critical context |
+
+## COMMON PATTERNS
+
+- **Storage**: Use `storage.ts` with JSON file for persistent state across sessions
+- **Once-per-session**: Track injected paths in Set to avoid duplicate injection
+- **Message injection**: Return `{ messages: [...] }` from event handlers
+- **Blocking**: Return `{ blocked: true, message: "reason" }` from PreToolUse
+
+## ANTI-PATTERNS (HOOKS)
+
+- **Heavy computation** in PreToolUse: Slows every tool call
+- **Blocking without clear reason**: Always provide actionable message
+- **Duplicate injection**: Track what's already injected per session
+- **Ignoring errors**: Always try/catch, log failures, don't crash session
diff --git a/src/tools/AGENTS.md b/src/tools/AGENTS.md
new file mode 100644
index 0000000..8d19041
--- /dev/null
+++ b/src/tools/AGENTS.md
@@ -0,0 +1,73 @@
+# TOOLS KNOWLEDGE BASE
+
+## OVERVIEW
+
+Custom tools extending agent capabilities: LSP integration (11 tools), AST-aware code search/replace, file operations with timeouts, background task management.
+
+## STRUCTURE
+
+```
+tools/
+├── ast-grep/           # AST-aware code search/replace (25 languages)
+│   ├── cli.ts          # @ast-grep/cli subprocess
+│   ├── napi.ts         # @ast-grep/napi native binding (preferred)
+│   ├── constants.ts, types.ts, tools.ts, utils.ts
+├── background-task/    # Async agent task management
+├── call-omo-agent/     # Spawn explore/librarian agents
+├── glob/               # File pattern matching (timeout-safe)
+├── grep/               # Content search (timeout-safe)
+├── interactive-bash/   # Tmux session management
+├── look-at/            # Multimodal analysis (PDF, images)
+├── lsp/                # 11 LSP tools
+│   ├── client.ts       # LSP connection lifecycle
+│   ├── config.ts       # Server configurations
+│   ├── tools.ts        # Tool implementations
+│   └── types.ts
+├── slashcommand/       # Slash command execution
+└── index.ts            # builtinTools export
+```
+
+## TOOL CATEGORIES
+
+| Category | Tools | Purpose |
+|----------|-------|---------|
+| LSP | lsp_hover, lsp_goto_definition, lsp_find_references, lsp_document_symbols, lsp_workspace_symbols, lsp_diagnostics, lsp_servers, lsp_prepare_rename, lsp_rename, lsp_code_actions, lsp_code_action_resolve | IDE-like code intelligence |
+| AST | ast_grep_search, ast_grep_replace | Pattern-based code search/replace |
+| File Search | grep, glob | Content and file pattern matching |
+| Background | background_task, background_output, background_cancel | Async agent orchestration |
+| Multimodal | look_at | PDF/image analysis via Gemini |
+| Terminal | interactive_bash | Tmux session control |
+| Commands | slashcommand | Execute slash commands |
+| Agents | call_omo_agent | Spawn explore/librarian |
+
+## HOW TO ADD A TOOL
+
+1. Create directory: `src/tools/my-tool/`
+2. Create files:
+   - `constants.ts`: `TOOL_NAME`, `TOOL_DESCRIPTION`
+   - `types.ts`: Parameter/result interfaces
+   - `tools.ts`: Tool implementation (returns OpenCode tool object)
+   - `index.ts`: Barrel export
+   - `utils.ts`: Helpers (optional)
+3. Add to `builtinTools` in `src/tools/index.ts`
+
+## LSP SPECIFICS
+
+- **Client lifecycle**: Lazy init on first use, auto-shutdown on idle
+- **Config priority**: opencode.json > oh-my-opencode.json > defaults
+- **Supported servers**: typescript-language-server, pylsp, gopls, rust-analyzer, etc.
+- **Custom servers**: Add via `lsp` config in oh-my-opencode.json
+
+## AST-GREP SPECIFICS
+
+- **Meta-variables**: `$VAR` (single node), `$$$` (multiple nodes)
+- **Languages**: 25 supported (typescript, tsx, python, rust, go, etc.)
+- **Binding**: Prefers @ast-grep/napi (native), falls back to @ast-grep/cli
+- **Pattern must be valid AST**: `export async function $NAME($$$) { $$$ }` not fragments
+
+## ANTI-PATTERNS (TOOLS)
+
+- **No timeout**: Always use timeout for file operations (default 60s)
+- **Blocking main thread**: Use async/await, never sync file ops
+- **Ignoring LSP errors**: Gracefully handle server not found/crashed
+- **Raw subprocess for ast-grep**: Prefer napi binding for performance