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 sutchan/Agent-Skills-Hub --skill capcutgit clone --depth 1 https://github.com/sutchan/Agent-Skills-HubWrote 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/sutchan/agent-skills-hub/capcut)<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/capcut"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/capcut/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/sutchan/agent-skills-hub/capcut"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/capcut.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 | $0.00129 | $0.02043 |
| Opus 5 | $0.00064 | $0.01022 |
| Sonnet 5 | $0.00026 | $0.00409 |
| Haiku 4.5 | $0.00013 | $0.00204 |
Grade A, and why
capcut 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.
This is a copy
92% identical to capcut — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
capcut
The short-form editing tool skill — edit to the script, drive the pace, ink the captions, tighten sound with
the license check, and ship safe + to spec. The agent plans and flags the hazards; the human executes and
approves; WoopSocial publishes the finished file. (Ships with tools/integrations/capcut.md.)
The POV: the edit serves the script — and "free" has fine print
CapCut earned its place as the default short-form editor: auto-captions in seconds, beat-sync, background removal,
trend templates, phone-to-desktop sync — with a ~15-minute ceiling by design (it's a short-form tool; route
long-form to Descript/Resolve). Two top-1% edges most creators learn the hard way. (1) The licensing fine
print: the June 2025 ToS grants ByteDance a perpetual, transferable, sublicensable license to anything
uploaded/synced (you keep copyright — it's a license, not ownership, stated precisely) — so client/NDA
material edits locally, never synced; and the music trap: free-library assets are personal-use only, and even
tracks labeled "Commercial use" are reported cleared for TikTok/CapCut platforms only — YouTube/IG claims
still happen, verify per track. (2) Check the tier before you build: features migrate behind Pro over time,
and the documented failure is hours of editing ending at a paywalled export. The craft line: the edit executes
what short-form-video-script designed — pacing, captions, and sound serve the beats; and auto-captions always
get an accuracy pass, because a wrong claim in a caption is a published error.
Read these first
- short-form-video-script — the beats this edit executes.
- brand-profile + design-and-templates (caption style/type/color) + voice-builder (any copy/TTS).
The framework: EDITS
(Depth: references/the-edits-framework.md.)
- E — Edit to the script: load the beats; cut everything that isn't in them; the hook lands in the first seconds; the last cut is the loop.
- D — Drive the pace: visual change every ~2–4s (jump cuts, punch-ins/keyframes, B-roll, text pops); beat-sync; scrub-test for dead stretches.
- I — Ink the captions: auto-captions + the mandatory accuracy pass; style once, save the preset; sound-off first; SRT/VTT export when copy travels.
- T — Tighten sound + effects (the license gate): license-check music BEFORE export (the "Commercial use"-is-TikTok-only trap); platform-native audio, licensed tracks, or ai-music-and-sound; effects sparingly.
- S — Ship safe + to spec: right resolution/fps per destination; ToS hygiene (local-only for client work); likeness/AI-disclosure handled; export → scheduling-and-queue → WoopSocial.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 98 lines · 129 tokens per session scan A b2ebc86b2e48
capcut is a skill published in the GitHub repository sutchan/Agent-Skills-Hub (2 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 2,043 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to capcut, differing in 20 lines, and is treated as a copy.
Other skills, from other repositories
iflytek-hyper-tts
A text-to-speech tool that turns written text into an MP3 recording. It can use an authorized voice and adjust speaking speed, volume, and pitch.
iflytek-voiceclone-tts
A tool for creating a speech model from recorded audio and then generating speech that uses the cloned voice. Voice cloning means training software to imitate a person’s voice.
animated-sketch-diagram
A tool for making animated diagrams and flowcharts in a hand-drawn ink style, with paper-like backgrounds, simple icons, and moving dots along connections. It produces a self-contained HTML file and can also create a looping GIF.
iflytek-video-translate
A tool that translates a video’s speech into another language and creates dubbed audio. Video localization means adapting video content for viewers who speak a different language.
iflytek-speed-transcription
Ultra-fast speech transcription using iFLYTEK Speed Transcription API. Transcribe audio files (WAV/PCM/MP3) up to 5 hours in 20 seconds per hour. Supports Chinese, English, and 202+ Chinese dialects with automatic language detection. Use when user asks to transcribe audio files, convert speech to text, or mentions…
iflytek-image-understanding
An image-analysis tool that describes pictures and answers questions about what they contain. It uses an AI vision service, which interprets visual content rather than only reading text files.