Skill of Skills
📚 resourceActiveCuratedcritical

multi-agent-shogun

by yohey-w

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

Stars

1.3k

Skill Type

🧪 Product Verification

Quality Score

175/200

License

MIT

Forks

277

Last Updated

Jun 11, 2026

Discovered

Mar 27, 2026

Validation

Passed

github.com/yohey-w/multi-agent-shogun

Quality Breakdown

175/ 200

Content Signals

✓Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
○Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

critical

Manual security review required. Use with extreme caution.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Multi-agent system designed to spawn and orchestrate parallel AI agents without explicit human approval gates per agent execution
  • Tmux-based automation framework for executing arbitrary AI agent tasks with bash/shell integration
  • Repository includes bootstrap/setup script (first_setup.sh) that modifies system configuration
  • CLAUDE.md and .claude/settings.json configuration files indicate persistent AI tool configuration modification
  • Android app with SSH/foreground service capabilities (SshForegroundService, SshManager) enabling remote command execution
  • System designed for autonomous operation: 'zero coordination overhead' suggests agents execute without interactive human approval