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 Engine-Room-Games/after-effects-mcp --skill style-guidegit clone --depth 1 https://github.com/Engine-Room-Games/after-effects-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/engine-room-games/after-effects-mcp/style-guide)<a href="https://agentmods.dev/skills/engine-room-games/after-effects-mcp/style-guide"><img src="https://agentmods.dev/badge/skills/engine-room-games/after-effects-mcp/style-guide/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/engine-room-games/after-effects-mcp/style-guide"><img src="https://agentmods.dev/badge/skills/engine-room-games/after-effects-mcp/style-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.01793 |
| Opus 5.5 | $0.00030 | $0.00717 |
| Sonnet 5.5 | $0.00015 | $0.00359 |
| Haiku 4.5 | $0.00007 | $0.00179 |
Grade A, and why
style-guide 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 1mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capturing a house style
A house style is the difference between an assistant that builds a lower third
and one that builds their lower third. It lives in house-style.md beside the
.aep file, and get_house_style reads it before any build task.
Your job here is to get one written with as little effort from the user as possible. They are a motion designer. They know exactly what their work looks like and will struggle to dictate it as a specification — so do not ask them to.
Two ways in. Prefer the first.
1. Read it off work they already like
This is far better than any questionnaire, because it produces real numbers instead of adjectives.
-
Ask which comp to learn from — "point me at something that looks the way you want everything to look."
-
get_compfor size and frame rate, thenget_layer_fullon the layers that carry the look: the text, the background, the accent shapes. -
Pull out the concrete values — hex colours, font families and sizes, tracking, corner radii, stroke widths, the position of things relative to the frame.
-
Read the keyframes too.
get_keyframesplus the ease settings tell you the timing signature: how long a standard in-animation takes, whether it overshoots, whether anything is ever linear. -
Show them what you found, in their language, and ask what to change:
Here's what I read off that comp: near-black background
#0B0D12, white text in Inter Semibold at 64px with slightly tight tracking, one green accent#3DC46E. Things scale in over about 0.4s with an overshoot to 108% and easy ease on both ends. Nothing sits perfectly still — there's a slow wiggle on the chip. Does that sound like your style, or was that comp a one-off? -
Write it with
set_house_style.
2. Ask, when there is nothing to read
Only if the project is empty or they have no reference. Keep it to four
questions, and offer concrete options rather than open ones — "dark or light
background?" beats "what's your palette?". Then build one small example, show it
with screenshot_frame, and refine from their reaction. Reacting is easier than
specifying.
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.
- 1mo ago Changed · +33 lines a327f3367126
- 1mo ago First seen · 124 lines · 74 tokens per session scan A 71ab89f47a07
style-guide is a skill published in the GitHub repository Engine-Room-Games/after-effects-mcp (37 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,793 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
photoshop-remove-background
Remove a Photoshop background in one recipe call. Use when the user says remove background, cut out, isolate subject, transparent background, or arka planı sil. Do not rasterize, duplicate, hide, select subject, or mask.
agent-reels
Find animation and video references on 1human, consult a human-agent shared library, and contribute public creations only with prior owner permission.
figma
Bring Figma into a HyperFrames video - rendered assets, brand tokens, components, storyboard frames as reconstructed motion (frames read as states, not slides), shaders and connector-assisted motion. Use when the person pastes a figma.com link or asks to use a Figma design, frame, logo or brand.
add-component
Add a SwiftUI component from ShipSwift. Use when the user says "add component", "add a view", "add X view", "I need a chart", "add animation", or wants a specific UI element.
figma-to-content
Use this to turn a Figma design into an AEM Edge Delivery Services (EDS / AEM / Franklin / Helix) content page in Document Authoring (DA, da.live). Triggers: "build this Figma frame in EDS", "turn this Figma design into a DA page", "publish this design to da.live", or providing a figma.com URL for a page. Reads the…
direct
Set a redesign direction for an existing website. Analyzes the user's intent, picks a palette and visual direction, and writes the target spec (PRODUCT.md, DESIGN.md, DESIGN.json) plus a reasoning trace at stardust/direction.md. Use when the user asks to redesign a site, refresh the design, set a new design direction…