No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ayush-that · MCP Server · ★ 144
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is sub-agents.directory safe to install? View the security audit →
Sub-Agents Directory Discover Claude Code sub-agents, prompts, and MCP servers. About · Getting Started · Contributing About Sub-Agents Directory is a curated collection of 100+ sub-agent prompts and MCP servers for Claude Code. Browse by category, search by keyword, or generate custom agents with AI. Features Searchable Directory — Find the right sub-agent for your task Categorized Prompts — Language specialists, DevOps, Security, AI/ML, and more MCP Server Registry — Extend Claude Code with external tools AI Rule Generator — Create custom sub-agents tailored to your needs One-Click Copy — Copy prompts directly to your clipboard Open in Claude/ChatGPT — Use prompts instantly in your favorite AI assistant Getting Started Open http://localhost:3000 to view the directory. Contributing We welcome contributions! To add a new sub-agent:
| Stars | 144 |
| Forks | 33 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 74.5734530520368/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-14 |
| Created | 2026-01-02 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~14k |
These tools work well together with sub-agents.directory for enhanced workflows:
Looking for a sub-agents.directory alternative? If you're comparing sub-agents.directory with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
10 Claude sessions running. What are they doing? Live dashboard — monitor, cost tracking, search, sub-agent vi
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
MaverickMCP - Personal Stock Analysis MCP Server
A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity
The memory + security kernel for AI agents. Strata: a signed append-only log, receipts on every write, exact-h
Explore other popular mcp server tools:
sub-agents.directory is 🐒 Sub-Agents Directory is a curated collection of 100+ sub-agent prompts and MCP servers for Claude Code.. It is categorized as a MCP Server with 144 GitHub stars.
sub-agents.directory is primarily written in TypeScript. It covers topics such as ai-agents, claude, claude-ai.
You can find installation instructions and usage details in the sub-agents.directory GitHub repository at github.com/ayush-that/sub-agents.directory. The project has 144 stars and 33 forks, indicating an active community.
sub-agents.directory is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to sub-agents.directory on Agent Skills Hub include claudepro-directory, claude-view, claude-code-workflows. 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: