Design and scaffold sub-agents
create-sub-agentskillsetup L3★3
richfrem/agent-plugins-skills ↗What it does
Design and generate Claude Code sub-agent markdown file
Best for
Bootstrapping specialized agents with explicit permissions and lifecycle hooks instead of generic LLM responses
Inputs
- · agent name or use-case description
Outputs
- · Agent .md file with YAML frontmatter (model, maxTokens, color, permissions, hooks) + system prompt
Requires
- · validate_agent.py
Preconditions
Agent purpose determined; placement confirmed (plugin vs project)
Failure modes
- · high-risk operations (add escalation posture)
- · placement conflict (confirm override)
Trust signals
- · design interview
- · placement discovery
- · example blocks in description