by harleyszhang · Agent Tool · ★ 123
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 123 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 58/100 |
| Open Issues | 2 |
| Last Updated | 2025-07-11 |
| Created | 2023-07-26 |
| Platforms | python |
| Est. Tokens | ~505k |
llmprofiler llm theoretical performance analysis tools and support params, flops, memory and latency analysis. 主要功能 支持 qwen2.5、qwen3 dense 系列模型。 支持张量并行推理模式。 支持 、、 等硬件以及主流 decoder-only 的自回归模型，可自行在配置文件中增加。 支持分析性能瓶颈，不同 是 还是 ，以及 的性能瓶颈。 支持输出每层和整个模型的参数量、计算量，内存和 。 推理时支持预填充和解码阶段分别计算内存和 latency、以及理论支持的最大 等等。 支持设置计算效率、内存读取效率（不同推理框架可能不一样，这个设置好后，可推测输出实际值）。 推理性能理论分析结果的格式化输出。 如何使用 使用方法，直接调用 文件中函数 函数并输入相关参数即可。...
These tools work well together with llm_counts for enhanced workflows:
Looking for a llm_counts alternative? If you're comparing llm_counts 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.
Enterprise-grade LLM automated deployment tool that makes AI servers truly "plug-and-play".
Are Copilots Local Yet? The frontier of local LLM Copilots for code completion, project generation, shell assi
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market
A command-line interface tool for serving LLM using vLLM.
irresponsible innovation. Try now at https://chat.dev/
Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: