Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/perso-ai/perso-dubbing-pluginnpx agentmods add skills/perso-ai/perso-dubbing-plugin/clipWrote 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/perso-ai/perso-dubbing-plugin/clip)<a href="https://agentmods.dev/skills/perso-ai/perso-dubbing-plugin/clip"><img src="https://agentmods.dev/badge/skills/perso-ai/perso-dubbing-plugin/clip.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 | $0.00059 | $0.01249 |
| Opus 5 | $0.00030 | $0.00624 |
| Sonnet 5 | $0.00012 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
clip 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/clip
Cut a video into short clips + reframe. Subtitles are not this skill's job — after cutting, the srt skill styles them (see the handoff below).
Entry points
-
Explicit timecodes ("cut 2:00–3:00 of this video") → cut the local file directly:
--video "<file>" --ranges "2:00-3:00,...". No STT, no key, no credits. -
AI highlight selection on an STT project →
--planthen--clips(the flow below). Needs the project's transcript + word timestamps. -
Raw video, "find the good moments" (no timecodes given) → you can't pick highlights without a transcript, so ask the user which they want:
- STT (proper selection, uses credits): run the
srtskill's STT first to create the project, then clip it with--plan/--clips. - Free (no STT): the user gives the timecodes and you cut them with
--video --ranges.
Proceed with their choice — don't run STT (which bills credits) without asking.
- STT (proper selection, uses credits): run the
Core rules
- Only the worker sees the raw key — never open, echo, or pass it as an argument.
- The key gate applies only to
--project/--plan/--clips.--video --rangesand--sidecarsare fully offline — never run a key check/registration for them. - Run in the background — encoding takes time.
- This skill shares the dubbing skill's libraries: the
dubbingfolder must be installed next toclip.
Flow
Phase 1 — plan. node scripts/clip.mjs --project <seq> --plan prints the summary's section map (topic guide) plus the full sentence transcript, each line as order [start-end] text.
Phase 2 — pick, then cut. Read the transcript and choose clips, each { "title": "...", "start_order": N, "end_order": M }. Rubric:
- Hook first — start on a sentence that grabs attention (question, bold claim, funny/surprising line).
- End where the moment resolves, not at the first complete sentence. Ride the beat to its end — the whole reaction, follow-through, and any secondary punchline. Read a few sentences past the apparent ending; keep them if still the same reaction.
- Cut at the transition — end just before the energy drops or the tone shifts (excited reaction → calm narration).
- Peak — favour funny / surprising / emotional / quotable moments; the high point often sits a sentence or two after the literal reveal.
- Length 30–90s — the worker warns when outside; prefer the full arc over a premature cut.
- Title — describes the moment; becomes the file name (
01_<title>.mp4).
What ships with it
2 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 · 57 lines · 59 tokens per session scan A 82db727a24da
clip is a skill published in the GitHub repository perso-ai/perso-dubbing-plugin (37 stars, last pushed 25d ago), licensed MIT. It adds 59 tokens to every session and 1,249 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 2026-08-30.
Other skills, from other repositories
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-shaders
Three.js shaders - GLSL, ShaderMaterial, uniforms, custom effects. Use when creating custom visual effects, modifying vertices, writing fragment shaders, or extending built-in materials.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…