by myunwang · Agent Tool · ★ 113
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🐙 盯着 Claude Code 的桌面宠物：随 agent 状态变表情、弹消息气泡、一键授权，并统计 token 用量与花费。本地优先、MIT。
| Stars | 113 |
| Forks | 20 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 50.5410463457025/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-13 |
| Created | 2026-07-01 |
| Platforms | claude-code, node |
| Est. Tokens | ~13k |
These tools work well together with LLMPET for enhanced workflows:
Looking for a LLMPET alternative? If you're comparing LLMPET with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of cr
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
Personal Assistant Wizard for Claude Code — npx pawmode
A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know
Explore other popular agent tool tools:
LLMPET is 🐙 盯着 Claude Code 的桌面宠物：随 agent 状态变表情、弹消息气泡、一键授权，并统计 token 用量与花费。本地优先、MIT。. It is categorized as a Agent Tool with 113 GitHub stars.
LLMPET is primarily written in JavaScript. It covers topics such as ai-agent, anthropic, claude.
You can find installation instructions and usage details in the LLMPET GitHub repository at github.com/myunwang/LLMPET. The project has 113 stars and 20 forks, indicating an active community.
LLMPET is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to LLMPET on Agent Skills Hub include palot, smart-ralph, navigator. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: