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/nle-export)<a href="https://agentmods.dev/skills/belagum/promptcut/nle-export"><img src="https://agentmods.dev/badge/skills/belagum/promptcut/nle-export.svg" alt="Measured on agentmods" 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 | $0.03418 |
| Opus 5 | $0.00059 | $0.01709 |
| Sonnet 5 | $0.00024 | $0.00684 |
| Haiku 4.5 | $0.00012 | $0.00342 |
Grade A, and why
nle-export scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editor hand-off: Premiere Pro, DaVinci Resolve, VEGAS Pro
PromptCut renders the mp4 itself; this skill instead writes a project the person finishes in their own editor. One command, three targets, one shared model:
plan.json ──build──▶ media + timing ──nle-from-plan──▶ export/timeline.json ──▶ .premiere.xml
├─▶ .resolve.xml
└─▶ .vegas.cs + .vegas.xml
Everything lands in <plan>_build/export/ (or --out DIR): the xml/cs files,
timeline.json (the neutral model, editable by hand), subs.srt, overlays/*.png
(title cards). Media is referenced by absolute path from <plan>_build/img|audio,
nothing is copied - keep that folder where it is or relink after moving.
Commands
python "${CLAUDE_PLUGIN_ROOT}/scripts/promptcut.py" nle-from-plan --plan plan.json --target premiere|resolve|vegas|all
[--use-clips] [--no-transitions] [--name X] [--out DIR] [--run] [--timeline-only]
python "${CLAUDE_PLUGIN_ROOT}/scripts/promptcut.py" nle-build --spec timeline.json --target ... [--out DIR] [--run]
nle-from-planneeds the media from a previousbuild(the real one or--fake); it never generates media itself. Without a build it reports gaps.--use-clipsplaces the rendered per-shot clips (clips/*.mp4, motion baked in) instead of stills with keyframes. Exact same look as the mp4, nothing to calibrate, but the motion is no longer editable. Requires a finishedbuild.--no-transitionsgives hard cuts. Default: the plan's transitions become Cross Dissolves (any xfade name maps to a dissolve).--run(VEGAS only) starts VEGAS Pro with the generated script; the project builds itself and is saved as<name>.vegnext to the script.--target allwrites every editor's files at once - cheap, do it when unsure which editor the person will open.doctorlists installed editors undernle.config --set vegas_exe=...when VEGAS is not auto-detected for--run.
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.
- 8d ago First seen · 213 lines · 118 tokens per session scan A 76ade0a9984e
nle-export is a skill published in the GitHub repository Belagum/promptcut (1 stars, last pushed 11d ago), licensed MIT. It adds 118 tokens to every session and 3,418 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…