📄 skillActiveCuratedhigh

hcom

by aannoo

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi

Supported Platforms

🤖 Claude Code

Stars

337

Skill Type

📖 Library & API Reference

Quality Score

129/200

License

MIT

Forks

43

Last Updated

Jun 11, 2026

Discovered

Apr 22, 2026

Validation

Passed

github.com/aannoo/hcom

Quality Breakdown

129/ 200

Content Signals

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

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
â—‹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

high

Broad system access required. Carefully review permissions before installing.

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 spawning and orchestration: Core functionality enables spawning, forking, and killing AI agents autonomously across terminals
  • Autonomous operation without human approval gates: Agents can message, observe, and subscribe to each other with automatic reactions ('React automatically')
  • Terminal/shell access: Commands like 'term', 'run', 'launch', 'daemon', 'relay' indicate execution capabilities in terminals and PTY manipulation
  • Install scripts present: install.sh and bootstrap.rs suggest automated installation and bootstrap processes
  • Inter-agent communication and control: Relay system, messaging, and hooks enable agents to command and control each other
  • Multiple AI vendor integrations: Hooks for Claude, Gemini, Codex, and OpenCode suggest this is a coordination layer for multiple AI agents