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 deifos/screenslick-mcp --skill skillgit clone --depth 1 https://github.com/deifos/screenslick-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/deifos/screenslick-mcp/skill)<a href="https://agentmods.dev/skills/deifos/screenslick-mcp/skill"><img src="https://agentmods.dev/badge/skills/deifos/screenslick-mcp/skill/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/deifos/screenslick-mcp/skill"><img src="https://agentmods.dev/badge/skills/deifos/screenslick-mcp/skill.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 | $0.00000 | $0.02421 |
| Opus 5.5 | $0.00000 | $0.00968 |
| Sonnet 5.5 | $0.00000 | $0.00484 |
| Haiku 4.5 | $0.00000 | $0.00242 |
Grade A, and why
screenslick-video-studio 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 16d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion Studio
You build videos live, in front of the user. They watch the ScreenSlick studio page: chat on the
left, a live Remotion preview, and a timeline where every layer you add appears as a clip they can
drag, trim, retime or delete. Hand edits write back to the same files you edit. Every message comes
with a <studio-context> block: the active project, the variant on screen, the playhead, the selected
clips and any attached frame (open attached images with your image viewer: Read in Claude Code,
view_image in Codex). If another agent started the chat, an <earlier-conversation> block recaps it.
The project (read references/format.md before your first edit)
projects/<slug>/
project.json fps, durationInFrames, variants (wide 1920x1080, mobile 1080x1920), fonts, background
layers.json the timeline: tracks → clips (frames!), markers
scenes/*.tsx custom visuals: one default-exported React component per file
assets/ voice, music, sfx, images, video, fonts
notes.md your cue sheet and the numbers behind sound choices
renders/ exports; never delete or overwrite
- Everything on the timeline is a clip in
layers.json, so the user can edit it. Never hide sounds, images or text inside scene code when they could be clips: music, voice and every SFX are audio clips; screenshots and logos are image clips; captions are a captions clip; overlays like film grain or a vignette are scene clips on their own track. - Scenes are for what clips can't express: rebuilt product UI, kinetic typography, diagrams,
backgrounds. A scene clip names a component (
"scene": "Hook"→scenes/Hook.tsx) and passesprops. Put words, colors and timings the user may want to change inprops, not hard-coded. - Frames are the unit everywhere.
tracks[0]is drawn on top. Give tracks and clips readable, stable ids (voice,music,sfx,scenes;hook,f2-card,sfx-whoosh-reveal) and anoteon cue clips saying why they sit where they sit ("whoosh 2f before the reveal cut"). - Read
layers.jsonright before editing it: the user may have changed it by hand. Keep their edits unless asked otherwise.
What ships with it
7 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.
- 16d ago Changed · +10 lines 9eccd0e75ca1
- 18d ago First seen · 131 lines · 0 tokens per session scan A 061e743ee5f3
screenslick-video-studio is a skill published in the GitHub repository deifos/screenslick-mcp (0 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,421 tokens. 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 2026-10-20.
screenslick-video-studio compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| screenslick-video-studiodeifos/screenslick-mcp | Skill | 0 | 18d ago | MIT | A | 0 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |