Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Belagum/promptcut/plugin install promptcutWrote 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/skills/belagum/promptcut/video-toolbox)<a href="https://agentmods.dev/skills/belagum/promptcut/video-toolbox"><img src="https://agentmods.dev/badge/skills/belagum/promptcut/video-toolbox/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/skills/belagum/promptcut/video-toolbox"><img src="https://agentmods.dev/badge/skills/belagum/promptcut/video-toolbox.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 | $0.00118 | $0.04551 |
| Opus 5 | $0.00059 | $0.02276 |
| Sonnet 5 | $0.00024 | $0.00910 |
| Haiku 4.5 | $0.00012 | $0.00455 |
Grade A, and why
video-toolbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromptCut video toolbox
A CLI toolbox, not a fixed pipeline. The person says what they want; you pick the commands. Every command prints JSON on stdout and progress on stderr.
Run everything as:
python "${CLAUDE_PLUGIN_ROOT}/scripts/promptcut.py" <command> [flags]
Use python on Windows, python3 on macOS/Linux. Add --help to any command.
Reply to the person in their own language.
Before the first job in a session
Run doctor. It reports ffmpeg, the OpenRouter key, pycapcut, the CapCut drafts
folder, installed editors (nle) and stock keys, plus a problems list. Fix only what the job needs:
a talking-head cut needs ffmpeg alone, image generation needs the key. If the
problems are missing packages or ffmpeg, run setup - it installs them itself;
only keys need the person.
Two modes of work
Single action — "cut 3 seconds", "add subtitles", "make it vertical", "drop the pauses", "put music under it". Call the one command that does it and report the output path. Do not build a plan for this.
Whole video from an idea or a script — write a plan.json storyboard, then
build. This is the mode for "make me a video about X", faceless shorts,
narrated explainers, ad reads.
Full video: the loop
- Turn the idea into shots. One shot = one spoken sentence + one picture.
8-14 words per shot for shorts, up to 25 for long form. Write the
voin the person's language; writeimage_promptin English (image models are much better at it) and keep a consistentimage.styleacross shots. - Write
plan.json(schema below).plan-new --out plan.jsongives a starter. build --plan plan.json --fake— free dry run with stub images and beeped voice. It proves the timing, subtitle splits and length. Show the person the duration and the shot list, not the stub video, unless they ask.build --plan plan.jsonfor real. Media is cached by content hash, so re-running after a text edit only pays for what changed.- Report the mp4 path, the duration and
spend_usd. Offer the CapCut draft (capcut-from-plan) or an editor project (nle-from-plan --target premiere|resolve|vegas, see the nle-export skill) if they may want to tweak by hand.
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.
- 9d ago First seen · 268 lines · 118 tokens per session scan A 9f0aabbf694a
video-toolbox is a skill published in the GitHub repository Belagum/promptcut (1 stars, last pushed 13d ago), licensed MIT. It adds 118 tokens to every session and 4,551 once invoked, about $0.0006 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.
Other skills, from other repositories
demo-shorts
Cut a vertical 9:16 Short (YouTube Shorts, Instagram Reels, TikTok) from a demo video project in one of four named styles — listicle (rapid numbered beats), cohost (split screen with presenter), flashcard (typographic interstitials), or glide (immersive pan). Use when the user asks for a "short", "shorts", "vertical…
demo-script
Writing the script and shot list for a demo video, and the demo.json manifest schema. Use when planning what a product video should say and show, writing voiceover narration, structuring scenes, or editing demo.json.
demo-assembly
Assembling and rendering a demo video with Remotion and ffmpeg — the timeline, transitions, captions, zoom-to-click, audio ducking, and diagnosing a render that comes out wrong. Use when rendering the final video, customising its look, or fixing timing, black frames or missing audio.
demo-capture
Craft and mechanics of capturing software on screen for a demo video — rehearsing a flow, staging a window, the action-script format, pacing to narration, and macOS permissions and coordinates. Use when recording an app, driving a UI for a video, debugging a capture that looks wrong, or when clicks land in the wrong…
capcut-edit
Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draftcontent.json, draftinfo.json, or cutting videos.
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…