fix: pedagogical review - add expected output, CLAUDE.md, fix consistency

Address findings from pedagogical review simulating a non-expert user:

- Add CLAUDE.md to project root (was referenced but missing)
- Fix README score from 12/9/1 to 13/8/1 (match feature-map.md)
- Add Expected Output sections to examples 01, 02, 05, 09, 10
- Create pipeline-output/ and briefings/ directories
- Add example ordering guidance in README
- Add plan requirements for examples 11/13 in prerequisites
- Add skill frontmatter explanation in GETTING-STARTED.md
- Explain Cowork/Dispatch with links in cowork-integration
- Expand .gitignore with node_modules and generated output files
- Add model override hints in agent frontmatter comments

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

CLAUDE.md

@@ -1,35 +1,49 @@
 # Claude Code Complete Agent
 
-This is a working companion repo for the article
-"Every OpenClaw Feature, Covered by Claude Code."
+## What this project is
 
-## What This Repo Does
+A companion repo for the article "Every OpenClaw Feature, Covered by
+Claude Code." It contains working configuration, 13 examples, and
+documentation that maps OpenClaw's 22 capabilities to Claude Code's
+ecosystem.
 
-It demonstrates that Claude Code's ecosystem (tools, MCP servers,
-plugins, hooks, agents, skills, and triggers) covers the same
-20 capabilities that made OpenClaw the fastest-growing open-source
-project in history.
+## How to use this
 
-## How to Use It
+1. Browse `examples/` and paste any prompt into this session
+2. Read `feature-map.md` for the full comparison table
+3. Follow `GETTING-STARTED.md` to turn this into your personal setup
 
-1. Open this directory in Claude Code: `claude`
-2. Try any example from `examples/` by pasting the prompt
-3. Explore agents in `.claude/agents/` and skills in `.claude/skills/`
-4. Review security hooks in `hooks/`
+## What is configured
 
-## Project Memory
+- **Agents** (`.claude/agents/`): researcher, writer, reviewer
+- **Skills** (`.claude/skills/`): daily-briefing, web-research, send-slack-message
+- **Hooks** (`hooks/`): pre-tool-use blocks dangerous commands, post-tool-use logs all actions
+- **Playwright MCP** (`.mcp.json`): disabled by default, enable for browser automation examples
+- **Permissions** (`.claude/settings.json`): safe defaults with deny list for destructive patterns
 
-This file is the project's persistent memory. Claude Code reads it
-at the start of every session. You can add notes, preferences, and
-context here. Unlike OpenClaw's vector-search memory, Claude Code
-uses a file hierarchy:
+## Project structure
 
-- `CLAUDE.md` (this file) - project-level instructions
-- `~/.claude/CLAUDE.md` - global personal instructions
-- `.claude/settings.json` - permissions and tool configuration
+```
+examples/           13 numbered examples, each with a prompt.md
+security/           Permission modes, Auto Mode, hooks, NemoClaw comparison
+memory/             How cross-session memory works
+automation/         Cron, launchd, /loop, /schedule
+messaging/          Channels (iMessage, Telegram, Discord), Slack, Dispatch
+browser/            Playwright MCP setup
+cowork-integration/ How Code + Cowork + Dispatch replicate OpenClaw
+pipeline-output/    Output from example 10 (full pipeline)
+briefings/          Output from daily-briefing skill
+```
 
-## Convention
+## Memory
 
-- All examples are self-contained. No dependencies to install.
-- Hooks use bash. They work on macOS and Linux.
-- MCP config in `.mcp.json` uses Playwright (browser automation).
+Session state and notes go in `memory/MEMORY.md`.
+This file (CLAUDE.md) is for instructions. MEMORY.md is for state.
+
+## Rules for this project
+
+- This is a demo repo. Do not add dependencies or build steps.
+- Keep examples self-contained. Each should work independently.
+- All output files go in `pipeline-output/` or `briefings/`.
+- Do not modify files in `security/` or `hooks/` without reviewing
+  the security implications.