📄 skillStalePromisinghigh

plugins-for-claude-natives

by team-attention

Claude Code plugins for power users

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

804

Skill Type

📖 Library & API Reference

Quality Score

114/200

License

MIT

Forks

109

Last Updated

Jul 24, 2026

Discovered

Apr 17, 2026

Validation

Passed

github.com/team-attention/plugins-for-claude-natives

Quality Breakdown

114/ 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

high

Broad system access required. Carefully review permissions before installing.

Stale

No commits in 90-365 days and no tagged releases.

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

Risk Assessment

  • Multi-agent spawning capability: 'agent-council' plugin explicitly orchestrates multiple AI agents (Gemini, GPT, Codex) and 'team-assemble' provides dynamic agent team orchestration
  • Shell script execution: Multiple .sh files present (council.sh, doubt-detector.sh, doubt-validator.sh, council-job.sh) that execute without clear approval gates
  • Install automation: bin/install.js and package.json with install scripts indicate bootstrap/setup automation
  • Persistent configuration modification: CLAUDE.md and AGENTS.md files suggest Claude behavior modification and agent configuration
  • External code execution: Plugins interface with external APIs (Gmail, Google Calendar, KakaoTalk, YouTube, Twitter) and execute Python/JavaScript scripts
  • Autonomous operation patterns: Scripts like council-job-worker.js suggest background job execution without explicit user approval per request

Related guides