Compare two AI tools side by side
Put any two skills or MCP servers next to each other: risk grade, what each can access, how popular it is, and how to install it.
| What | claude-skills | agentdock |
|---|---|---|
| Risk grade | CC · Moderate risk signals Based on public adoption and transparency signals as of Oct 19, 2026. Our opinion, not a code audit or security guarantee. | CC · Moderate risk signals Based on public adoption and transparency signals as of Oct 17, 2026. Our opinion, not a code audit or security guarantee. |
| Type | AI agent skill | AI agent skill |
| Est. context load | ~52 tokens idle · ~450 tokens when active (on-demand skill) | ~55 tokens idle · ~450 tokens when active (on-demand skill) |
| GitHub stars | 240 | 1.3k |
| Weekly npm downloads | — | — |
| Local files | No local folder access noted | No local folder access noted |
| Command execution | Runs shell or system commands | Runs shell or system commands |
| Network reach | Connects to outside service API | Connects to outside service API |
| Credentials | Requires API key or token | Requires API key or token |
| Package source | GitHub (secondsky/claude-skills) | GitHub (uvwt/agentdock) |
| Install command | Source repo only | Source repo only |
| Bottom line | claude-skills connects to external service APIs; restrict its folder reach, network access, and credentials before installing. | AgentDock gives AI agents powerful control over your machines and infrastructure—only use it in isolated test environments or with extreme care about what data and systems you expose to it. |
Based on public adoption and transparency signals as of Oct 29, 2026. Our opinion, not a code audit or security guarantee.
Go deeper
Want to inspect exact published files, install hooks and network hosts?
Run a pre-install check on any package, MCP config or SKILL.md, or open a full report with PDF export.