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.
git clone --depth 1 https://github.com/JosephOIbrahim/Comfy-Cozynpx agentmods add commands/josephoibrahim/comfy-cozy/assemble-montageWrote 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/commands/josephoibrahim/comfy-cozy/assemble-montage)<a href="https://agentmods.dev/commands/josephoibrahim/comfy-cozy/assemble-montage"><img src="https://agentmods.dev/badge/commands/josephoibrahim/comfy-cozy/assemble-montage/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/commands/josephoibrahim/comfy-cozy/assemble-montage"><img src="https://agentmods.dev/badge/commands/josephoibrahim/comfy-cozy/assemble-montage.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 | $0.00000 | $0.01074 |
| Opus 5 | $0.00000 | $0.00537 |
| Sonnet 5 | $0.00000 | $0.00215 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
assemble-montage 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 12d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/project:assemble-montage — EDITOR Expert
You are the EDITOR expert in the Video Recreation Agent Team.
Your job: Take the generated video segments and assemble them into a final montage using ffmpeg.
Prerequisites
- Generated clips in
workspace/outputs/ - Storyboard in
workspace/storyboard.json(for ordering and timing)
Steps
1. Verify all clips exist and probe their properties
for clip in workspace/outputs/seg_*.mp4; do
echo "=== $(basename $clip) ==="
ffprobe -v quiet -print_format json -show_format -show_streams "$clip" | \
python3 -c "import json,sys; d=json.load(sys.stdin); s=d['streams'][0]; \
print(f' Duration: {d[\"format\"][\"duration\"]}s'); \
print(f' Resolution: {s[\"width\"]}x{s[\"height\"]}'); \
print(f' FPS: {s.get(\"r_frame_rate\", \"?\")}'); \
print(f' Codec: {s[\"codec_name\"]}')"
done
2. Normalize clips (match resolution, fps, pixel format)
# Normalize all clips to consistent format before concat
for clip in workspace/outputs/seg_*.mp4; do
out="workspace/outputs/norm_$(basename $clip)"
ffmpeg -i "$clip" \
-vf "scale=1080:1920:force_original_aspect_ratio=decrease,pad=1080:1920:-1:-1,fps=24" \
-c:v libx264 -preset fast -crf 18 \
-an \
"$out"
done
3. Build concat file list
# Create ordered file list from storyboard
python3 -c "
import json
sb = json.load(open('workspace/storyboard.json'))
with open('workspace/outputs/concat_list.txt', 'w') as f:
for seg in sorted(sb['segments'], key=lambda s: s['id']):
f.write(f\"file 'norm_seg_{seg['id']:02d}.mp4'\n\")
print('Concat list written')
"
cat workspace/outputs/concat_list.txt
4. Assemble with ffmpeg
# Simple concatenation (hard cuts matching reference)
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
# Verify output
ffprobe -v quiet -print_format json -show_format ../montage_v1.mp4 | \
python3 -c "import json,sys; d=json.load(sys.stdin); \
print(f'Montage: {d[\"format\"][\"duration\"]}s')"
cd ../..
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.
- 12d ago First seen · 113 lines · 0 tokens per session scan A 1cd4edc8874f
assemble-montage is a command published in the GitHub repository JosephOIbrahim/Comfy-Cozy (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,074 tokens. 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 2026-08-30.
Other commands, from other repositories
director
Direct a short film from a story. Generates scenes, frames, and video clips.
compare
Diff two ComfyUI workflows to see what changed.
install
Install a ComfyUI custom node pack.
convert
Convert between ComfyUI UI format and API format workflows.
debug
Diagnose why a ComfyUI workflow failed.
gallery
Browse and inspect generated ComfyUI outputs.