setup

setup is a command for Claude Code from JosephOIbrahim/Comfy-Cozy. It costs 0 tokens per session (5,523 once invoked), scanned A, original, MIT.

An automated setup command for a Video Recreation Agent Team in a ComfyUI agent repository. ComfyUI is a node-based application for creating image and video workflows.

In plain words
What is it for?
Use it to detect the current project path, find ComfyUI in common locations, and check whether ComfyUI is running on its local port.
Why use it?
It removes repetitive setup work by locating the repository and looking for an existing ComfyUI installation or running service.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is `cd workspace/outputs && ffmpeg -f concat -safe 0 -i concat_list.txt -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p ../montage_v1.mp4`.

Good fit Use it to detect the current project path, find ComfyUI in common locations, and check whether ComfyUI is running on its local port.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Comfy-Cozy
agentmods
npx agentmods add commands/josephoibrahim/comfy-cozy/setup

Made for: Claude Code.

Wrote 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.

agentmods badge for setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/josephoibrahim/comfy-cozy/setup/github.svg)](https://agentmods.dev/commands/josephoibrahim/comfy-cozy/setup)
Your own site
<a href="https://agentmods.dev/commands/josephoibrahim/comfy-cozy/setup"><img src="https://agentmods.dev/badge/commands/josephoibrahim/comfy-cozy/setup/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.

agentmods 80×15 button for setup

Your own site · 80×15
<a href="https://agentmods.dev/commands/josephoibrahim/comfy-cozy/setup"><img src="https://agentmods.dev/badge/commands/josephoibrahim/comfy-cozy/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.05523
Opus 5.5 $0.00000 $0.02209
Sonnet 5.5 $0.00000 $0.01105
Haiku 4.5 $0.00000 $0.00552

Measured 1mo ago against content hash 62bdaa168a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://127.0.0.1:8188/system_stats 2>/dev/null && echo "ComfyUI is running on port 8188"
video-recreation-agent/.claude/commands/setup.md · 564 lines

How it starts

The opening of the file, as written. The whole thing — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/project:setup — Automated Setup for Video Recreation Agent Team

You are setting up the Video Recreation Agent Team inside this comfyui-agent repo. Run every step below automatically. Don't ask permission — just do it, report what happened.

Step 1: Detect the current repo location

echo "AGENT_PATH=$(pwd)"

Store this as AGENT_PATH. This is the comfyui-agent repo root.

Step 2: Find ComfyUI installation

Search these common locations. Use the FIRST one that has main.py inside it:

# Check common ComfyUI install locations
for path in \
  "$HOME/ComfyUI" \
  "$HOME/comfyui" \
  "/Applications/ComfyUI" \
  "/opt/ComfyUI" \
  "C:/ComfyUI" \
  "D:/ComfyUI" \
  "G:/COMFYUI_Database" \
  "G:/ComfyUI" \
  "$HOME/Documents/ComfyUI" \
  "$HOME/Desktop/ComfyUI" \
  "/mnt/c/ComfyUI" \
  "/mnt/d/ComfyUI"; do
  if [ -f "$path/main.py" ]; then
    echo "FOUND: $path"
    break
  fi
done

Also try to find it by checking if ComfyUI is currently running:

# If ComfyUI is running, we can ask it
curl -s http://127.0.0.1:8188/system_stats 2>/dev/null && echo "ComfyUI is running on port 8188"

If you can't find ComfyUI's folder automatically, ask the user ONE question:

"Where is ComfyUI installed? Paste the folder path (the one with main.py in it):"

If ComfyUI is running but you don't know the folder, that's OK — the bridge only needs HTTP access. Set COMFYUI_PATH to empty and note it.

Step 3: Create all workspace directories

mkdir -p workspace/reference
mkdir -p workspace/keyframes
mkdir -p workspace/workflows
mkdir -p workspace/outputs
mkdir -p workspace/qa/frames
echo "✓ Workspace directories created"

Step 4: Create the .claude/commands directory if it doesn't exist

mkdir -p .claude/commands
echo "✓ Commands directory ready"

Step 5: Write the bridge.env config

Using the paths you detected, write config/bridge.env:

mkdir -p config
cat > config/bridge.env << 'ENVEOF'
# Video Recreation Agent — Bridge Configuration
# Auto-generated by /project:setup

COMFYUI_PATH=${DETECTED_COMFYUI_PATH}
COMFYUI_HOST=127.0.0.1
COMFYUI_PORT=8188
AGENT_PATH=${DETECTED_AGENT_PATH}
WORKSPACE=${DETECTED_AGENT_PATH}/workspace
ENVEOF
echo "✓ Bridge config written to config/bridge.env"

Read the full file on GitHub · 564 lines

Changes

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.

  1. 1mo ago First seen · 564 lines · 0 tokens per session scan A 62bdaa168a78

Subscribe to this mod's changes

setup is a command published in the GitHub repository JosephOIbrahim/Comfy-Cozy (25 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,523 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.