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 Maciejdziuba/youtube-skills --skill after-effects-scriptinggit clone --depth 1 https://github.com/Maciejdziuba/youtube-skillsWrote 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/maciejdziuba/youtube-skills/after-effects-scripting)<a href="https://agentmods.dev/skills/maciejdziuba/youtube-skills/after-effects-scripting"><img src="https://agentmods.dev/badge/skills/maciejdziuba/youtube-skills/after-effects-scripting/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/maciejdziuba/youtube-skills/after-effects-scripting"><img src="https://agentmods.dev/badge/skills/maciejdziuba/youtube-skills/after-effects-scripting.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 | $0.00148 | $0.01577 |
| Opus 5 | $0.00074 | $0.00788 |
| Sonnet 5 | $0.00030 | $0.00315 |
| Haiku 4.5 | $0.00015 | $0.00158 |
Grade A, and why
after-effects-scripting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
After Effects, driven from the shell
After Effects exposes an AppleScript command, DoScript, that runs ExtendScript
inside the live application. That is the whole bridge. Nothing is installed, no
MCP server, no CEP panel.
osascript -e 'tell application "Adobe After Effects 2026" to DoScript "$.evalFile(\"/tmp/ae/build.jsx\")"'
Before anything else
- After Effects must be open, with a project.
Preferences → Scripting & Expressions → Allow Scripts to Write Files and Access Networkmust be on. Nothing works without it.- macOS may need Automation permission for your terminal (System Settings → Privacy & Security → Automation).
- Confirm the bridge before building anything:
osascript -e 'tell application "Adobe After Effects 2026" to DoScript "var f=new File(\"/tmp/ae/ping.txt\"); f.open(\"w\"); f.write(\"alive \"+app.project.numItems); f.close();"'
Adjust the app name to the installed version. DoScript returning 1 instead of
0 means AE is busy or blocked by a modal dialog — see When it looks hung.
The loop — this is the skill
Never judge a change you have not looked at. The entire value of this workflow is that you can see your own output and fix it, instead of guessing from a description. One cycle:
- Write
build.jsx— idempotent: it wipes and rebuilds the comp every run. - Run it. Read
err.txtandprog.txt. - Render proof frames, stitch a contact sheet, open the image and look at it.
- Fix what you actually see. Repeat.
scripts/ae-run.sh does steps 2–3 in one command:
~/.claude/skills/after-effects-scripting/scripts/ae-run.sh /tmp/ae "MY COMP"
It prints BUILD: OK or the error with a line number, waits for AE to finish
flushing PNGs to disk, and prints the path of a timestamped contact sheet. Read
that image with your file-reading tool. Do not skip this step — every serious
mistake in a build is invisible in the code and obvious in the frame.
Use the helper library
What ships with it
6 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.
- 11d ago First seen · 127 lines · 148 tokens per session scan A 7e0413d2bcaf
after-effects-scripting is a skill published in the GitHub repository Maciejdziuba/youtube-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 148 tokens to every session and 1,577 once invoked, about $0.0007 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
drive-after-effects
Use this skill when inspecting or mutating a live After Effects project through LayerCake MCP tools (aehoststatus, aeopenproject, aecloseproject, aeprojectcontext, aeprojectsummary, aelist, aegetitemrefs, aepatchproject, aesaveproject, aeevalscript, aedocs). Trigger even when phrased as "look at the comp", "rename…
bilibili-upload
A workflow for using the sau command-line tool to log in to Bilibili, a Chinese video-sharing platform, check an account, and upload videos.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
youtube
Use whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation. Manages videos, playlists, comments, captions, subscriptions, thumbnails, analytics, and more.
remotion-video
Use when you need to render an actual video file with Remotion — React compositions, the Composition/Sequence/TransitionSeries graph, transitions, burned-in word-by-word captions from a transcript, automatic silence removal, b-roll overlays, headless CI renders, and a final MP4 or MOV. NOT writing the script, hook…
visual-identity-prompt
Writes a comprehensive visual identity prompt for a show, channel, or publication — a master brief that defines the complete visual language and can be used to art-direct any asset in the project's visual system.