sub-agents.directory
Reduces engineering time spent designing agent prompts and MCP server configurations by providing production-ready templates.
๐ Sub-Agents Directory is a curated collection of 100+ sub-agent prompts and MCP servers for Claude Code.
- Find pre-built agent prompts to extend Claude's capabilities for specific coding tasks
- Discover MCP servers compatible with Claude Code for specialized development workflows
- Browse curated sub-agent templates to accelerate building custom AI coding assistants
Reduces engineering time spent designing agent prompts and MCP server configurations by providing production-ready templates. Accelerates Claude Code adoption across teams by eliminating prompt engineering guesswork.
Development teams integrating Claude Code agents into CI/CD pipelines or automation workflows.
https://github.com/ayush-that/sub-agents.directory
By ayush-that
How to Get It
claude plugins install ayush-that/sub-agents.directory
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me find pre-built agent prompts to extend Claude's capabilities for specific coding tasks
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good โ it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 136 GitHub stars; 4 contributors; last commit 41d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying โ
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 136 GitHub stars; 4 contributors; last commit 41d ago; license MIT.