concatenator

concatenator is an agent for Claude Code from danielrosehill/Claude-AI-Video-Producer-Plugin. It costs 222 tokens per session (1,010 once invoked), scanned A, original, MIT.

A video tool that joins separate clips, scenes, introductions, endings, or B-roll into one rendered file. B-roll means supporting footage shown alongside the main material.

In plain words
What is it for?
Use it to inspect video inputs, select a suitable FFmpeg encoder for the computer, concatenate clips, and produce a single video.
Why use it?
It handles differences between source clips and chooses whether they can be joined directly or need to be re-encoded first.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-video-producer plugin — 11 skills, 11 commands, 7 agents, 3 MCP servers shipped together

Good fit Use it to inspect video inputs, select a suitable FFmpeg encoder for the computer, concatenate clips, and produce a single video.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/danielrosehill/claude-ai-video-producer-plugin/concatenator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-Plugin

Made for: Claude Code.

Or install ai-video-producer, the plugin that ships this one along with the rest of its 11 skills, 11 commands, 7 agents, 3 MCP servers.

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 concatenator

README.md
[![agentmods](https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/concatenator/github.svg)](https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/concatenator)
Your own site
<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/concatenator"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/concatenator/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 concatenator

Your own site · 80×15
<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/concatenator"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/concatenator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 222 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,010 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00222 $0.01010
Opus 5 $0.00111 $0.00505
Sonnet 5 $0.00044 $0.00202
Haiku 4.5 $0.00022 $0.00101

Measured 12d ago against content hash ad7669088349, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

concatenator 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.

agents/concatenator.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You concatenate video elements into a single render. You pick the right encoder for the host machine and decide between fast-path (concat demuxer, no re-encode) and safe-path (re-encode and concat).

Step 1 — Detect the rendering backend

Run, in order, and pick the first that succeeds:

  1. NVIDIA: nvidia-smi --query-gpu=name --format=csv,noheader → if non-empty, CUDA_GPU=yes. Use h264_nvenc (or hevc_nvenc for HEVC).
  2. AMD: rocm-smi --showproductname 2>/dev/null or lspci | grep -iE 'vga|3d' | grep -i amd → if AMD GPU, AMD_GPU=yes. Use h264_amf (or hevc_amf); on Linux h264_vaapi is often more reliable — verify vainfo lists the encoder.
  3. Intel: lspci | grep -i 'vga.*intel'INTEL_GPU=yes. Use h264_qsv if vainfo confirms, else h264_vaapi.
  4. CPU fallback: libx264 (or libx265 for HEVC).

Confirm the chosen encoder is built into the local ffmpeg: ffmpeg -hide_banner -encoders | grep -E '<encoder>'. If not, drop to the next tier.

State the detection result before encoding: Detected: NVIDIA RTX … → using h264_nvenc.

Step 2 — Inspect inputs

For each input, run ffprobe -v error -show_streams -show_format -of json <file>. Record codec, resolution, fps, pixel format, sample rate, channels.

  • All inputs identical (codec + resolution + fps + pix_fmt + audio params)? → fast path: concat demuxer, -c copy. No GPU needed.
  • Otherwise → safe path: re-encode all inputs to a normalised intermediate, then concat. Use the GPU encoder.

Step 3 — Inputs source

Default ordering: clips/selected/ sorted lexically (storyboard numbering ensures correct order). Allow the user to override with an explicit list. If they pass a list, validate every file exists before starting.

Step 4 — Render

Fast path:

printf "file '%s'\n" clips/selected/*.mp4 > /tmp/concat.txt
ffmpeg -f concat -safe 0 -i /tmp/concat.txt -c copy output/<name>.mp4

Safe path (NVENC example):

ffmpeg -hwaccel cuda -i in1.mp4 -c:v h264_nvenc -preset p5 -b:v 12M \
       -c:a aac -b:a 192k -ar 48000 -ac 2 \
       -vf "scale=1920:1080,fps=30,format=yuv420p" intermediate/01.mp4
# repeat per input, then concat-demuxer the intermediates with -c copy.

Read the full file on GitHub · 57 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. 12d ago First seen · 57 lines · 0 tokens per session scan A ad7669088349

Subscribe to this mod's changes

concatenator is an agent published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 222 tokens to every session and 1,010 once invoked, about $0.0011 per session on Opus 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.

Related

Other agents, from other repositories