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 KyaniteLabs/kinocut --skill kinocut-repurposegit clone --depth 1 https://github.com/KyaniteLabs/kinocutWrote 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/kyanitelabs/kinocut/kinocut-repurpose)<a href="https://agentmods.dev/skills/kyanitelabs/kinocut/kinocut-repurpose"><img src="https://agentmods.dev/badge/skills/kyanitelabs/kinocut/kinocut-repurpose/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/kyanitelabs/kinocut/kinocut-repurpose"><img src="https://agentmods.dev/badge/skills/kyanitelabs/kinocut/kinocut-repurpose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 18 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium MCP Rug Pull · line 24 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00035 | $0.00919 |
| Opus 5.5 | $0.00014 | $0.00368 |
| Sonnet 5.5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
kinocut-repurpose 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kinocut Repurpose
This is a pre-kernel, path-based v1 skill. It guides an agent to produce a good short clip from one local video using only shipped Kinocut tools. Do not invent commands, providers, kernels, schedulers, uploaders, or publishing steps.
Plugin runtime
The host starts the pinned Kinocut server from this plugin's mcp.json.
Use its MCP tools directly. Do not install another copy, copy skills into
another host, or change another tool's configuration. CLI examples below apply
only when kino is already available; otherwise use the equivalent MCP tools.
Current Tools
Use these shipped surfaces only:
- MCP:
video_repurpose_plan, thenvideo_repurpose. - CLI:
repurpose-plan, thenrepurpose. - Optional support tools when needed:
info,video-ai-transcribe,generate-subtitles,subtitles,resize,normalize-audio,thumbnail,storyboard,video-quality-check.
Useful CLI shape:
kino --format json info input.mp4
kino repurpose-plan input.mp4 --platforms youtube-shorts instagram-reel tiktok -o repurpose-out
kino repurpose input.mp4 --platforms youtube-shorts instagram-reel tiktok -o repurpose-out --min-score 0
kino video-quality-check repurpose-out/youtube_shorts.mp4
Required Flow
- Inspect the source path first with
infoorvideo_info. Confirm duration, resolution, aspect, and audio presence. - Choose one short-clip intent and two or three platforms. Prefer
youtube-shorts,instagram-reel, andtiktokfor vertical clips unless the user explicitly asks for horizontal or square. - Run
repurpose-plan/video_repurpose_planbefore rendering. Review therepurpose_manifest.jsonfor platform outputs, aspect ratios, target LUFS, max duration, and planned review artifacts. - Render with
repurpose/video_repurposeonly after the plan is plausible. - Inspect the rendered manifest, thumbnails, storyboards, and release checkpoint output.
- Stop at human review. Do not publish, schedule, upload, or claim final approval.
What ships with it
1 file 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.
- 4d ago Changed · -15 lines 3d04b4131a43
- 16d ago Changed · -2 tokens per session 3a90bb05cf8f
- 1mo ago First seen · 101 lines · 37 tokens per session scan A 49a901a9c79b
kinocut-repurpose is a skill published in the GitHub repository KyaniteLabs/kinocut (223 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 919 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
ai-b-roll-motion-graphics
Insert contextual B-roll cutaways, animated data charts, lower thirds, and callout overlays on video timelines.
auto-captions-subtitles
Generate synchronized word-by-word animated captions and translated subtitles for video timelines.
multicam-podcast-video-editor
Synchronize multi-camera podcast recordings by audio waveform and switch camera angles on the active speaker.
silence-removal-audio-cleanup
Remove dead air, pauses, and filler words from video and audio timelines with automatic music ducking.
tiktok-reels-shorts-editor
Reframe horizontal 16:9 footage into 9:16 vertical short-form videos with subject tracking and captions.
levea-ai-video-editor
Plan, execute, and verify timeline video edits through the autonomousedit MCP tool.