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 JmsLdrn/capcut-mcp --skill capcut-reelsgit clone --depth 1 https://github.com/JmsLdrn/capcut-mcpWrote 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/jmsldrn/capcut-mcp/capcut-reels)<a href="https://agentmods.dev/skills/jmsldrn/capcut-mcp/capcut-reels"><img src="https://agentmods.dev/badge/skills/jmsldrn/capcut-mcp/capcut-reels.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 | $0.01167 |
| Opus 5 | $0.00059 | $0.00583 |
| Sonnet 5 | $0.00024 | $0.00233 |
| Haiku 4.5 | $0.00012 | $0.00117 |
Grade A, and why
capcut-reels 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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CapCut reels pipeline
This skill drives real CapCut desktop projects through the capcut MCP (tools named
mcp__capcut__*) plus a small set of companion tools. It is the repeatable process behind a
series of vertical real-estate reels; it generalizes to any short-form video assembled from
clips + captions + motion graphics.
Prerequisites
- capcut MCP installed and connected (
claude mcp add capcut ...). Tools appear asmcp__capcut__*. - CapCut desktop installed, with the drafts you want to edit saved locally.
- ffmpeg + ffprobe on PATH (durations/resolutions; final encodes).
- HyperFrames (optional) for motion-graphic overlays / full-screen animated scenes.
- WhisperFlow (optional) for transcription → captions/subtitles.
The one rule that matters most
Close CapCut on the draft before saving. CapCut autosaves on a timer and will clobber your
edits. capcut_save refuses when CapCut is running or the draft's .locked file exists — do not
force past that unless you are certain the app is closed. All times at the tool boundary are in
seconds.
Workflow
- Inspect.
capcut_list_draftsto find the draft;capcut_read_timelineto see canvas, fps, tracks, and every segment (ids, media, start/duration in seconds, layer). Note the segmentids you'll act on. - Start from a known-good base. For a fresh build,
capcut_clone_draft(optionallyempty:true) rather than authoring JSON from scratch — cloning is the only reliable way to get valid CapCut structure. To edit in place, just operate on the existing draft. - Prepare media (companion tools, outside CapCut):
- Motion graphics / animated scenes → HyperFrames, rendered to
.mp4(or alpha.mov). - Captions → WhisperFlow transcript; convert cue timings to seconds for
capcut_add_text, or burn them in HyperFrames if you want styled/animated captions. - Use ffprobe to confirm each asset's duration before placing it so timings line up.
- Motion graphics / animated scenes → HyperFrames, rendered to
- Assemble in the draft (session edits accumulate in memory):
capcut_add_video/_image/_audio— place media atatSecon a track.capcut_add_text— captions/titles (needs a text-template draft; seeCAPCUT_TEMPLATE_DRAFT).capcut_add_track— separate layers for b-roll, captions, music.capcut_move_segment/_trim_segment/_split_segment/_delete_segment— re-cut and retime.capcut_set_props— scale, position, rotation, opacity, volume, speed, visibility.capcut_raw_patch— escape hatch for effects/transitions/rich text (inspect a template first; these are best-effort and version-sensitive).
- Validate, then save.
capcut_validate(overlaps, duplicate ids, missing media) → fix anything flagged → close CapCut →capcut_save(writes a.mcpbakbackup, atomic write, re-validates). Usecapcut_discardto drop an unsaved session. - Reopen in CapCut to review, then export from the app (or encode the assembled pieces with ffmpeg).
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.
- 6d ago First seen · 73 lines · 118 tokens per session scan A 6fcba1e45114
capcut-reels is a skill published in the GitHub repository JmsLdrn/capcut-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,167 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
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.