clip-maker

clip-maker is a command for coding agents from IvanLutsenko/awac-ai-agent-plugins. It costs 23 tokens per session (1,251 once invoked), scanned A, original, MIT.

A tool that turns a horizontal video into short vertical clips for Reels, Shorts, or TikTok. It transcribes the video, finds notable moments, crops and cuts them, adds subtitles, and can write accompanying social-media text.

In plain words
What is it for?
Use it to produce clips of a chosen length, select moments automatically, transcribe in a chosen language, burn subtitles into the video, and optionally generate posting copy.
Why use it?
It removes the manual work of searching through a long video, editing clips for a phone-shaped screen, and preparing captions. It can start from either a local video or a web address.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the clip-maker plugin — 5 skills, 3 commands, 2 agents shipped together

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.

agentmods
npx agentmods add commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker
Clone the repo
git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins

Or install clip-maker, the plugin that ships this one along with the rest of its 5 skills, 3 commands, 2 agents.

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 clip-maker

README.md
[![agentmods](https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker.svg)](https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker)
Your own site
<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.01251
Opus 5 $0.00012 $0.00626
Sonnet 5 $0.00005 $0.00250
Haiku 4.5 $0.00002 $0.00125

Measured 3d ago against content hash e22f854438be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clip-maker 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 3d 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.

plugins/clip-maker/commands/clip-maker.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clip Maker — Full Pipeline

Create vertical (9:16) clips from a horizontal video, optimized for Reels/Shorts/TikTok.

Arguments

Parse $ARGUMENTS for:

  • <video_path_or_url>required, path to source video OR YouTube/web URL
  • --duration N — target clip duration in seconds (default: 60)
  • --auto — skip manual moment selection, use all found moments
  • --no-subtitles — don't burn subtitles into clips
  • --api — use OpenAI Whisper API instead of local whisper
  • --no-copy — skip social media copy generation
  • --language LANG — transcription language (default: ru)
  • --prompt "terms" — domain-specific terms for whisper (improves recognition of jargon, names, abbreviations)

Pipeline

Execute steps sequentially. Report progress to the user after each step.

Step 1: Check dependencies

bash ${CLAUDE_PLUGIN_ROOT}/scripts/install-deps.sh [--api if user passed --api]

If it fails, stop and report what's missing.

Step 2: Download if URL

If <video_path> looks like a URL (starts with http://, https://, or youtube.com, youtu.be):

VIDEO_PATH=$(bash ${CLAUDE_PLUGIN_ROOT}/scripts/download-video.sh "<url>" ~/Downloads)

The script outputs the downloaded file path. Use it as <video_path> for subsequent steps.

Step 3: Setup output directory

Create output directory next to the video: {video_dir}/{video_name}_clips/

Step 4: Transcribe

bash ${CLAUDE_PLUGIN_ROOT}/scripts/transcribe.sh "<video_path>" "<output_dir>" [--api] [--language LANG] [--prompt "terms"]

This produces <output_dir>/transcript.json.

Step 5: Find interesting moments

Launch the moment-finder agent:

Agent(subagent_type="clip-maker:moment-finder", model="opus", prompt="
Analyze the transcript and find the most engaging moments for vertical clips.

- Transcript path: <output_dir>/transcript.json
- Target clip duration: <duration> seconds
- Output path: <output_dir>/moments.json

Read the transcript, find the best moments, and write moments.json.
")

Read the full file on GitHub · 165 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. 3d ago First seen · 165 lines · 23 tokens per session scan A e22f854438be

Subscribe to this mod's changes

clip-maker is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,251 once invoked, about $0.0001 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.