Skill of Skills
🔌 pluginActiveCuratedhigh

agents-observe

by simple10

Real-time observability of claude code sessions & multi-agents.

Stars

590

Skill Type

📊 Data Fetching & Analysis

Quality Score

152/200

License

MIT

Forks

55

Last Updated

Jun 11, 2026

Discovered

Apr 6, 2026

Validation

Passed

github.com/simple10/agents-observe

Quality Breakdown

152/ 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
✓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

  • Docker execution: Repository includes Dockerfile and requires Docker for server operation, enabling container-based code execution
  • Persistent configuration modification: .claude/settings.json, .claude-plugin/, and .mcp.json indicate persistent Claude environment modifications
  • Multi-agent orchestration: AGENTS.md and multi-agent session capture indicate spawn and coordination of multiple agents
  • Bootstrap/installation automation: Claude plugin system with marketplace integration and auto-start MCP server on Claude invocation
  • Hook-based automation: .codex/hooks.json suggests automated execution triggers outside direct user control
  • Node.js script execution: Requires Node.js for hook scripts that run automatically during plugin operations