mirror of https://github.com/SuperClaude-Org/SuperClaude_Framework.git synced 2025-12-29 16:16:08 +00:00

Files

kazuki 2ec23b14e5 feat: implement lazy loading architecture with PM Agent Skills migration

## Changes

### Core Architecture
- Migrated PM Agent from always-loaded .md to on-demand Skills
- Implemented lazy loading: agents/modes no longer installed by default
- Only Skills and commands are installed (99.5% token reduction)

### Skills Structure
- Created `superclaude/skills/pm/` with modular architecture:
  - SKILL.md (87 tokens - description only)
  - implementation.md (16KB - full PM protocol)
  - modules/ (git-status, token-counter, pm-formatter)

### Installation System Updates
- Modified `slash_commands.py`:
  - Added Skills directory discovery
  - Skills-aware file installation (→ ~/.claude/skills/)
  - Custom validation for Skills paths
- Modified `agent_personas.py`: Skip installation (migrated to Skills)
- Modified `behavior_modes.py`: Skip installation (migrated to Skills)

### Security
- Updated path validation to allow ~/.claude/skills/ installation
- Maintained security checks for all other paths

## Performance

**Token Savings**:
- Before: 17,737 tokens (agents + modes always loaded)
- After: 87 tokens (Skills SKILL.md descriptions only)
- Reduction: 99.5% (17,650 tokens saved)

**Loading Behavior**:
- Startup: 0 tokens (PM Agent not loaded)
- `/sc:pm` invocation: ~2,500 tokens (full protocol loaded on-demand)
- Other agents/modes: Not loaded at all

## Benefits

1. **Zero-Footprint Startup**: SuperClaude no longer pollutes context
2. **On-Demand Loading**: Pay token cost only when actually using features
3. **Scalable**: Can migrate other agents to Skills incrementally
4. **Backward Compatible**: Source files remain for future migration

## Next Steps

- Test PM Skills in real Airis development workflow
- Migrate other high-value agents to Skills as needed
- Keep unused agents/modes in source (no installation overhead)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

2025-10-21 05:17:53 +09:00

899 B

Raw Blame History

name, description, version, author, category, migrated

name	description	version	author	category	migrated
pm	Project Manager Agent - Self-improvement workflow executor that documents implementations, analyzes mistakes, and maintains knowledge base continuously	1.0.0	SuperClaude	meta	true

PM Agent (Project Manager Agent)

Skills-based on-demand loading implementation.

Token Efficiency:

Startup: 0 tokens (not loaded)
Description: ~100 tokens (this file)
Full load: ~2,500 tokens (loaded when /sc:pm is invoked)

Activation:

/sc:pm command
Session start (auto-activation)
Post-implementation documentation needs
Mistake detection and analysis

Implementation: See implementation.md for full protocol

Modules: Support files in modules/ directory

token-counter.md - Dynamic token calculation
git-status.md - Git repository state detection
pm-formatter.md - Output structure and formatting

899 B Raw Blame History

PM Agent (Project Manager Agent)

899 B

Raw Blame History