diff --git a/AGENTS.md b/AGENTS.md
index f82cd18..1a960fa 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,7 +1,7 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** 2026-01-01T21:15:00+09:00
-**Commit:** 490c0b6
+**Generated:** 2026-01-02T00:10:00+09:00
+**Commit:** b0c39e2
 **Branch:** dev
 
 ## OVERVIEW
@@ -17,7 +17,7 @@ oh-my-opencode/
 │   ├── hooks/         # 22 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
+│   ├── features/      # Claude Code compatibility + core features - see src/features/AGENTS.md
 │   ├── config/        # Zod schema, TypeScript types
 │   ├── auth/          # Google Antigravity OAuth - see src/auth/AGENTS.md
 │   ├── shared/        # Utilities: deep-merge, pattern-matcher, logger, etc. - see src/shared/AGENTS.md
@@ -36,12 +36,14 @@ oh-my-opencode/
 | 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 and types.ts |
+| Add skill | `src/features/builtin-skills/` | Create skill dir with SKILL.md |
 | 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/Gemini 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 |
 | Background agents | `src/features/background-agent/` | manager.ts for task management |
+| Skill MCP | `src/features/skill-mcp-manager/` | MCP servers embedded in skills |
 | Interactive terminal | `src/tools/interactive-bash/` | tmux session management |
 | CLI installer | `src/cli/install.ts` | Interactive TUI installation |
 | Doctor checks | `src/cli/doctor/checks/` | Health checks for environment |
@@ -74,6 +76,7 @@ oh-my-opencode/
 - **Broad tool access**: Prefer explicit `include` over unrestricted access
 - **Sequential agent calls**: Use `background_task` for parallel execution
 - **Heavy PreToolUse logic**: Slows every tool call
+- **Self-planning for complex tasks**: Spawn planning agent (Prometheus) instead
 
 ## UNIQUE STYLES
 
@@ -128,19 +131,22 @@ bun test               # Run tests
 
 | File | Lines | Description |
 |------|-------|-------------|
-| `src/index.ts` | 697 | Main plugin orchestration, all hook/tool initialization |
-| `src/cli/config-manager.ts` | 670 | JSONC parsing, environment detection, installation |
-| `src/auth/antigravity/fetch.ts` | 622 | Token refresh, URL rewriting, endpoint fallbacks |
-| `src/tools/lsp/client.ts` | 612 | LSP protocol, stdin/stdout buffering, JSON-RPC |
-| `src/hooks/anthropic-context-window-limit-recovery/executor.ts` | 555 | Session compaction, multi-stage recovery pipeline |
-| `src/agents/sisyphus.ts` | 505 | Orchestrator prompt, delegation strategies |
+| `src/index.ts` | 723 | Main plugin orchestration, all hook/tool initialization |
+| `src/cli/config-manager.ts` | 669 | JSONC parsing, environment detection, installation |
+| `src/auth/antigravity/fetch.ts` | 621 | Token refresh, URL rewriting, endpoint fallbacks |
+| `src/tools/lsp/client.ts` | 611 | LSP protocol, stdin/stdout buffering, JSON-RPC |
+| `src/auth/antigravity/response.ts` | 598 | Response transformation, streaming |
+| `src/auth/antigravity/thinking.ts` | 571 | Thinking block extraction/transformation |
+| `src/hooks/anthropic-context-window-limit-recovery/executor.ts` | 554 | Session compaction, multi-stage recovery pipeline |
+| `src/agents/sisyphus.ts` | 504 | Orchestrator prompt, delegation strategies |
 
 ## NOTES
 
-- **Testing**: Bun native test (`bun test`), BDD-style `#given/#when/#then`
+- **Testing**: Bun native test (`bun test`), BDD-style `#given/#when/#then`, 360+ tests
 - **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
 - **JSONC support**: Config files support comments (`// comment`, `/* block */`) and trailing commas
 - **Claude Code Compat**: Full compatibility layer for settings.json hooks, commands, skills, agents, MCPs
+- **Skill MCP**: Skills can embed MCP server configs in YAML frontmatter
diff --git a/src/features/AGENTS.md b/src/features/AGENTS.md
index a70292e..c719f21 100644
--- a/src/features/AGENTS.md
+++ b/src/features/AGENTS.md
@@ -13,6 +13,8 @@ features/
 │   ├── manager.test.ts
 │   └── types.ts
 ├── builtin-commands/           # Built-in slash command definitions
+├── builtin-skills/             # Built-in skills (playwright, etc.)
+│   └── */SKILL.md              # Each skill in own directory
 ├── 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
@@ -20,6 +22,9 @@ features/
 ├── claude-code-plugin-loader/  # Load external plugins from installed_plugins.json
 ├── claude-code-session-state/  # Session state persistence
 ├── opencode-skill-loader/      # Load skills from OpenCode and Claude paths
+├── skill-mcp-manager/          # MCP servers embedded in skills
+│   ├── manager.ts              # Lazy-loading MCP client lifecycle
+│   └── types.ts
 └── hook-message-injector/      # Inject messages into conversation
 ```
 
@@ -72,6 +77,19 @@ Disable features in `oh-my-opencode.json`:
 - **Timing**: PreToolUse, PostToolUse, UserPromptSubmit, Stop
 - **Format**: Returns `{ messages: [{ role: "user", content: "..." }] }`
 
+## SKILL MCP MANAGER
+
+- **Purpose**: Manage MCP servers embedded in skill YAML frontmatter
+- **Lifecycle**: Lazy client loading, session-scoped cleanup
+- **Config**: `mcp` field in skill's YAML frontmatter defines server config
+- **Tool**: `skill_mcp` exposes MCP capabilities (tools, resources, prompts)
+
+## BUILTIN SKILLS
+
+- **Location**: `src/features/builtin-skills/*/SKILL.md`
+- **Available**: `playwright` (browser automation)
+- **Disable**: `disabled_skills: ["playwright"]` in config
+
 ## ANTI-PATTERNS (FEATURES)
 
 - **Blocking on load**: Loaders run at startup, keep them fast
diff --git a/src/tools/AGENTS.md b/src/tools/AGENTS.md
index 747ff75..1edff46 100644
--- a/src/tools/AGENTS.md
+++ b/src/tools/AGENTS.md
@@ -29,6 +29,8 @@ tools/
 │   ├── storage.ts      # File I/O operations
 │   ├── utils.ts        # Formatting, filtering
 │   └── tools.ts        # Tool implementations
+├── skill/              # Skill loading and execution
+├── skill-mcp/          # Skill-embedded MCP invocation
 ├── slashcommand/       # Slash command execution
 └── index.ts            # builtinTools export
 ```
@@ -45,6 +47,7 @@ tools/
 | Multimodal | look_at | PDF/image analysis via Gemini |
 | Terminal | interactive_bash | Tmux session control |
 | Commands | slashcommand | Execute slash commands |
+| Skills | skill, skill_mcp | Load skills, invoke skill-embedded MCPs |
 | Agents | call_omo_agent | Spawn explore/librarian |
 
 ## HOW TO ADD A TOOL