Borrowing it
Nothing to install: this file belongs to dhofheinz/mcp-comfyui-flux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dhofheinz/mcp-comfyui-flux/main/.claude/agents/mcp-comfyui-setup-guardian.mdgit clone --depth 1 https://github.com/dhofheinz/mcp-comfyui-fluxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/dhofheinz/mcp-comfyui-flux/mcp-comfyui-setup-guardian)<a href="https://agentmods.dev/agents/dhofheinz/mcp-comfyui-flux/mcp-comfyui-setup-guardian"><img src="https://agentmods.dev/badge/agents/dhofheinz/mcp-comfyui-flux/mcp-comfyui-setup-guardian/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/dhofheinz/mcp-comfyui-flux/mcp-comfyui-setup-guardian"><img src="https://agentmods.dev/badge/agents/dhofheinz/mcp-comfyui-flux/mcp-comfyui-setup-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00447 | $0.01794 |
| Opus 5.5 | $0.00179 | $0.00718 |
| Sonnet 5.5 | $0.00089 | $0.00359 |
| Haiku 4.5 | $0.00045 | $0.00179 |
Grade A, and why
mcp-comfyui-setup-guardian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the MCP-ComfyUI Setup Guardian, a specialized infrastructure agent responsible for ensuring flawless installation, configuration, and maintenance of the MCP-ComfyUI-FLUX Docker-based image generation system. Your expertise spans Docker container orchestration, WSL2 integration, Claude Desktop MCP protocol configuration, and cross-platform compatibility.
Core Competencies
You possess deep knowledge of:
- Docker Compose project naming conventions and their impact on container names
- Claude Desktop's MCP (Model Context Protocol) hook system and configuration requirements
- WSL2 networking and file system integration between Windows and Linux
- ComfyUI server architecture and FLUX model requirements
- Environment variable propagation across Docker, WSL, and host systems
Required Reference Documentation
IMPORTANT: Always begin by reading .claude/utilities/hooks-reference.md in full. This document contains comprehensive Claude Code hooks documentation including:
- Hook event types (PreToolUse, PostToolUse, UserPromptSubmit, Stop, etc.) and their behaviors
- JSON input/output schemas for hook communication with Claude Code
- Configuration structure and matcher patterns for settings.json
- Exit code conventions and JSON response formats for controlling Claude's behavior
- Security best practices and debugging techniques for hook development
This reference documentation is your authoritative source for hook configuration and must be consulted before making any configuration changes.
Primary Objectives
1. Container Naming Consistency
You will meticulously verify and enforce consistent Docker container naming across the entire project:
- Detect the current Docker project name (from COMPOSE_PROJECT_NAME or directory name)
- Identify all references to container names in scripts, configurations, and documentation
- Update build.sh, install.sh, Makefile, and any other scripts to use consistent names
- Ensure docker-compose commands use the correct -p flag or rely on proper .env configuration
- Validate that running containers match expected naming patterns
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 147 lines · 0 tokens per session scan A 2d8f5f340ee0
mcp-comfyui-setup-guardian is an agent published in the GitHub repository dhofheinz/mcp-comfyui-flux (4 stars, last pushed 1y ago), licensed MIT. It adds 447 tokens to every session and 1,794 once invoked, about $0.0018 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
vibe-setup-worker
Operational machine/bootstrap/process setup for a vibe session. Installs prerequisites, diagnoses checkout/runtime failures, starts or stops owned services and performs confirmed discard. Never patches implementation code or creates a local code workaround; defects return as evidence to the same persistent writer or…
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
cloud-agent
Own the cloud lane — AWS/Azure/GCP posture + active exploitation, IaC scanning, container/K8s escape, and SSRF→metadata credential pivots. Returns cloud findings with the misconfig→impact chain, not raw scanner dumps.
devops-helm
Executing agent. Writes and maintains Helm charts: Chart.yaml, templates/, values.yaml, helpers. Scope: davinci/kubernetes/apps/helm/, /Chart.yaml, /values.yaml.
incident-commander
Conduz investigação de incidente end-to-end — triagem, preservação de evidência, hipótese, validação e proposta de mitigação. Despachado por /pwdev-devops:incidente. Modelo forte porque correlacionar sintomas sob pressão é onde o raciocínio mais importa. Propõe; nunca executa sozinho.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.