SlavaSexton/ComfyUI-Agent-Kit
One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt recipes, 581 templates, plus standalone Seedance, Krea and MiniMax H3 skills. Hardware-aware selecti
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add comfyui -- npx -y comfyui-mcp $ npx degit SlavaSexton/ComfyUI-Agent-Kit/agents ./rig-comfyui-agent-kit/agents
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add comfyui -- npx -y comfyui-mcp $ npx degit SlavaSexton/ComfyUI-Agent-Kit/claude-code/skills/comfyui .claude/skills/comfyui $ npx degit SlavaSexton/ComfyUI-Agent-Kit/claude-code/skills/krea .claude/skills/krea $ npx degit SlavaSexton/ComfyUI-Agent-Kit/claude-code/skills/minimax-h3 .claude/skills/minimax-h3 $ npx degit SlavaSexton/ComfyUI-Agent-Kit/claude-code/skills/seedance .claude/skills/seedance
$ curl -fsSL --create-dirs -o .claude/agents/claude_md_activation.md https://raw.githubusercontent.com/SlavaSexton/ComfyUI-Agent-Kit/master/agents/claude/claude_md_activation.md This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| comfyui-mcp · "comfyui" | npm | 2.5k |
Skills (4)
Subagents (1)
| claude_md_activation | — |
Similar rigs
zalogarcia/zalo-claude-code-setup
One command to turn Claude Code into a production-grade AI engineering environment. 7 agents, 6 commands, 9 skills, 3 multi-agent workflows, 16 shared rules, guard hooks, and 4 MCP servers — with an interactive architecture visualizer.
Orchestrator 13.9k tok ·
Kairos-ai-agent/kairos-code
Self-hosted multi-agent coding pipeline with an enforced review gate and a cost ledger — you don't ship what the agent didn't pass. (AGPL-3.0)
Skill Collector 5.1k tok ·
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·