Claude Code Subagents support!

This release adds support for Claude Code's new subagents feature!

Added

• Claude Code Specialized Subagents - New agents to offload specific tasks for improved efficiency:
  • test-runner.md - Handles test execution and failure analysis with minimal toolset
  • context-fetcher.md - Retrieves information from files while checking context to avoid duplication
  • git-workflow.md - Manages git operations, branches, commits, and PR creation
  • file-creator.md - Creates files, directories, and applies consistent templates
• Agent Detection Pattern - Single check at process start with boolean flags for efficiency
• Subagent Integration across all instruction files with automatic fallback for non-Claude Code users

Changed

• Instruction Files - All updated to support conditional agent usage:
  • execute-tasks.md - Uses git-workflow (branch management, PR creation), test-runner (full suite), and context-fetcher (loading lite files)
  • execute-task.md - Uses context-fetcher (best practices, code style) and test-runner (task-specific tests)
  • plan-product.md - Uses file-creator (directory creation) and context-fetcher (tech stack defaults)
  • create-spec.md - Uses file-creator (spec folder) and context-fetcher (mission/roadmap checks)
• Standards Files - Updated for conditional agent usage:
  • code-style.md - Uses context-fetcher for loading language-specific style guides
• Setup Scripts - Enhanced to install Claude Code agents:
  • setup-claude-code.sh - Downloads all agents to ~/.claude/agents/ directory

Improved

• Context Efficiency - Specialized agents use minimal context for their specific tasks
• Code Organization - Complex operations delegated to focused agents with clear responsibilities
• Error Handling - Agents provide targeted error analysis and recovery strategies
• Maintainability - Cleaner main agent code with operations abstracted to subagents
• Performance - Reduced context checks through one-time agent detection pattern

Technical Details

• Each agent uses only necessary tools (e.g., test-runner uses only Bash, Read, Grep, Glob)
• Automatic fallback ensures compatibility for users without Claude Code
• Consistent IF has_[agent_name]: pattern reduces code complexity
• All agents follow Agent OS conventions (branch naming, commit messages, file templates)

First round of efficiency improvements (more to come!)

Added

• New mission-lite.md file generation in product initialization for efficient AI context usage
• New spec-lite.md file generation in spec creation for condensed spec summaries
• New execute-task.md instruction file for individual task execution with TDD workflow
• Task execution loop in execute-tasks.md that calls execute-task.md for each parent task
• Language-specific code style guides:
  • standards/code-style/css-style.md for CSS and TailwindCSS
  • standards/code-style/html-style.md for HTML markup
  • standards/code-style/javascript-style.md for JavaScript
• Conditional loading blocks in best-practices.md and code-style.md to prevent duplicate context loading
• Context-aware file loading throughout all instruction files

Changed

• Optimized plan-product.md to generate condensed versions of documents
• Enhanced create-spec.md with conditional context loading for mission-lite and tech-stack files
• Simplified technical specification structure by removing multiple approach options
• Made external dependencies section conditional in technical specifications
• Updated execute-tasks.md to use minimal context loading strategy
• Improved execute-task.md with selective reading of relevant documentation sections
• Modified roadmap progress check to be conditional and context-aware
• Updated decision documentation to avoid loading decisions.md and use conditional checks
• Restructured task execution to follow typical TDD pattern (tests first, implementation, verification)

Improved

• Context efficiency by 60-80% through conditional loading and lite file versions
• Reduced duplication when files are referenced multiple times in a workflow
• Clearer separation between task-specific and full test suite execution
• More intelligent file loading that checks current context before reading
• Better organization of code style rules with language-specific files

Fixed

• Duplicate content loading when instruction files are called in loops
• Unnecessary loading of full documentation files when condensed versions suffice
• Redundant test suite runs between individual task execution and overall workflow