Initial commit: Ajarbot with optimizations

Features:
- Multi-platform bot (Slack, Telegram)
- Memory system with SQLite FTS
- Tool use capabilities (file ops, commands)
- Scheduled tasks system
- Dynamic model switching (/sonnet, /haiku)
- Prompt caching for cost optimization

Optimizations:
- Default to Haiku 4.5 (12x cheaper)
- Reduced context: 3 messages, 2 memory results
- Optimized SOUL.md (48% smaller)
- Automatic caching when using Sonnet (90% savings)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

.claude/skills/adapter-dev/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: adapter-dev
+description: Help develop and debug messaging platform adapters for ajarbot
+user-invocable: true
+disable-model-invocation: true
+allowed-tools: Read, Grep, Glob, Edit, Bash
+context: fork
+agent: Plan
+---
+
+# Adapter Development Skill
+
+You are helping develop messaging platform adapters for ajarbot using the OpenClaw-inspired architecture.
+
+## When invoked
+
+1. **Analyze the request**: Understand what adapter work is needed
+2. **Check existing patterns**: Review `adapters/slack/` and `adapters/telegram/` for patterns
+3. **Follow the base contract**: All adapters must implement `BaseAdapter` from `adapters/base.py`
+4. **Test the implementation**: Suggest tests and validation steps
+
+## Key files to reference
+
+- `adapters/base.py` - Base adapter interface
+- `adapters/runtime.py` - Runtime integration
+- `adapters/slack/adapter.py` - Slack Socket Mode example
+- `adapters/telegram/adapter.py` - Telegram example
+- `README_ADAPTERS.md` - Architecture documentation
+
+## Common tasks
+
+### Create new adapter
+1. Create `adapters/<platform>/adapter.py`
+2. Implement required methods from `BaseAdapter`
+3. Define capabilities (threads, reactions, max length, etc.)
+4. Add to `bot_runner.py`
+5. Update config template
+
+### Debug adapter issues
+1. Check `validate_config()` returns true
+2. Verify credentials format
+3. Test `health_check()` method
+4. Review async event handler registration
+5. Check message chunking logic
+
+### Update existing adapter
+1. Read current implementation
+2. Understand the change request
+3. Follow existing patterns
+4. Preserve backward compatibility
+5. Update documentation
+
+## Security considerations
+
+- Never log credentials or tokens
+- Validate all user input before processing
+- Use platform-specific rate limits
+- Handle errors gracefully
+- Respect user allowlists
+
+## Output format
+
+Provide:
+1. Clear explanation of changes
+2. Code implementation
+3. Configuration updates needed
+4. Testing steps
+5. Documentation updates

.claude/skills/adapter-dev/examples/usage.md

@@ -0,0 +1,53 @@
+# Adapter Development Skill - Usage Examples
+
+## Example 1: Create a new Discord adapter
+
+```
+/adapter-dev create a Discord adapter using discord.py
+```
+
+The skill will:
+- Analyze existing Slack/Telegram adapters
+- Create `adapters/discord/adapter.py`
+- Implement BaseAdapter with Discord-specific logic
+- Add configuration section
+- Provide setup instructions
+
+## Example 2: Debug connection issues
+
+```
+/adapter-dev why isn't my Telegram adapter connecting?
+```
+
+The skill will:
+- Check config validation
+- Review credential format
+- Inspect health_check() implementation
+- Test async handlers
+- Suggest fixes
+
+## Example 3: Add reaction support
+
+```
+/adapter-dev add emoji reaction support to Slack adapter
+```
+
+The skill will:
+- Review capabilities declaration
+- Implement `send_reaction()` method
+- Update Slack API calls
+- Test the feature
+- Document the change
+
+## Example 4: Optimize chunking
+
+```
+/adapter-dev improve markdown-aware chunking for Telegram
+```
+
+The skill will:
+- Review current chunking logic
+- Implement better markdown parsing
+- Preserve code blocks and formatting
+- Test with long messages
+- Update documentation