- Document modern AI development workflow using specialized agents
- Add guidelines for when to use git worktree/subagents vs main conversation
- Define agent roles: ticket mgmt, design, code, test, docs, review
- Include implementation examples with Task tool
- Update test count (35 → 54) with new market_schedule tests
Closes#9
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>