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 agentmods add commands/engine-room-games/after-effects-mcp/init-after-effectsgit 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/commands/engine-room-games/after-effects-mcp/init-after-effects)<a href="https://agentmods.dev/commands/engine-room-games/after-effects-mcp/init-after-effects"><img src="https://agentmods.dev/badge/commands/engine-room-games/after-effects-mcp/init-after-effects.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 | $0.00025 | $0.00876 |
| Opus 5 | $0.00013 | $0.00438 |
| Sonnet 5 | $0.00005 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
init-after-effects 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 6d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up After Effects
The user has just connected these tools and wants to start working. Take them all the way from nothing to a first build. They are a motion designer, not a developer — they should never be asked to open a terminal, edit JSON, or read a file path they did not ask about.
$ARGUMENTS is the folder they named, if they named one.
Work through these in order, and stop at the first one that needs something from them. Do not run ahead and report four steps at once.
1. Install the panel — before they open After Effects
Call check_setup. It is read-only and safe.
Do not ask them to open After Effects yet. The panel only loads when AE launches, so installing while AE is still closed means it is simply there when they open it — no restart to ask for. If AE is already running you have to ask for one, which is why this step comes first.
-
Everything green — say so in one line and move on.
-
Anything red — explain what
setup_panelis about to do before calling it: it copies a small panel into their Adobe extensions folder and switches on the Adobe setting that allows unsigned panels. Both are user-level and reversible. Call it, then:- if
afterEffectsRunningwas false, ask them to open After Effects; - if it was true, ask them to quit and reopen it.
Then
check_setupagain to confirm. - if
If it still fails, load the ae-setup topic of ae_guide and work through it.
Do not improvise CEP diagnostics.
2. Where does the project live?
Call init_project. Pass dir when you know it — from $ARGUMENTS, or from
what the user says. If you do not know, ask before calling: "which folder
should this project live in? A new empty one is fine."
Never invent a path. If the tool reports it could not work out where to write,
that is exactly what it means — ask, then call again with dir.
Tell them the folder it created and what is in it, in one sentence. Do not paste the file list.
3. Now bring up After Effects
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.
- 6d ago First seen · 85 lines · 25 tokens per session scan A bdab098e998b
init-after-effects is a command published in the GitHub repository Engine-Room-Games/after-effects-mcp (6 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 876 once invoked, about $0.0001 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 commands, from other repositories
pixel-help
Show help for pixel art commands and skills.
pixel-new
Create a new pixel art sprite with optional size and palette presets.
change-fx
How to customize character images and sounds.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.