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.
npx skills add musyta-labs/mcpCut --skill video-editinggit clone --depth 1 https://github.com/musyta-labs/mcpCutWrote 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/musyta-labs/mcpcut/video-editing)<a href="https://agentmods.dev/skills/musyta-labs/mcpcut/video-editing"><img src="https://agentmods.dev/badge/skills/musyta-labs/mcpcut/video-editing/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/musyta-labs/mcpcut/video-editing"><img src="https://agentmods.dev/badge/skills/musyta-labs/mcpcut/video-editing.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 | $0.00055 | $0.01069 |
| Opus 5 | $0.00028 | $0.00535 |
| Sonnet 5 | $0.00011 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
video-editing 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 10d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing video through mcpCut
Works the same against a self-hosted server (http://127.0.0.1:8100/mcp) or
the hosted service at https://mcpcut.com/mcp (bearer token, browser editor
on top — the user sees your edits live at mcpcut.com/projects).
You are connected to a real video editor. It keeps projects: immutable timeline snapshots with a journaled history. Every tool call that edits returns the full updated project snapshot — always work from the latest returned snapshot, never from memory of an earlier one.
Conventions that make your edits reliable
- Errors come back as data, not exceptions: a failed call returns
{"error": "<reason>"}. Read it, fix the cause, retry deliberately — never retry the identical call in a loop. - Element ids, media ids, track ids are in every snapshot. Use ids from the latest snapshot; ids never survive a delete.
- Times are seconds (floats). Positions like
posaccept presets ("center","top","bottom"...). - One gesture = one tool call. The journal (
editor_get_history) records each named operation; prefer several precise calls over one clever one. - Long operations (export, captions, analysis) run synchronously and can take minutes on big media — call them once and wait.
The core workflow
- Create:
editor_create_project(optionally withmetadatatags). - Ingest:
editor_add_media(project_id, source)—sourceis a local path or an http(s) URL (URL import downloads server-side). The returned media entry carries duration/resolution once probed. - Assemble:
editor_add_clip(project_id, media_id, start_time, duration, trim_start)places footage on the timeline;editor_trim_clip,editor_split_clip,editor_move_clip,editor_resize_cliprefine it. Extra layers:editor_add_video_track/editor_add_audio_track. - Dress:
editor_add_text(project_id, content, start, duration, pos, size)for titles;editor_add_overlayfor images/GIFs/video overlays;editor_add_music(project_id, source)for a music bed;editor_set_transform(+editor_set_keyframesfor motion),editor_set_color,editor_add_transition. - Captions (if the ASR extra is installed):
editor_auto_captions (project_id)transcribes the timeline audio and lays word-timed captions.editor_update_textsfixes any wording afterwards. - Check before rendering:
editor_validate(project_id)reports structural problems;editor_render_preview(project_id, at_time)returns a frame so you can see the composition at a timestamp. - Export:
editor_export(project_id)renders the final file and returns a download path/URL. Exports are swept after a retention window (24 h by default) — tell the user to save the file, or re-export.
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.
- 10d ago First seen · 89 lines · 55 tokens per session scan A c6dac14ad15e
video-editing is a skill published in the GitHub repository musyta-labs/mcpCut (1 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,069 once invoked, about $0.0003 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.