after-effects-mcp: Instructions file for Claude Code

CLAUDE.md

after-effects-mcp CLAUDE.md is an instructions file for Claude Code from Engine-Room-Games/after-effects-mcp. It costs 29,765 tokens per session, scanned C, original, MIT.

Repository instructions for an MCP server that lets an AI control Adobe After Effects 2026. It covers compositions, layers, animation, effects, text, shapes, masks, footage, templates, screenshots, and batch operations.

In plain words
What is it for?
Use them when developing or documenting After Effects automation, including animation, visual effects, text, imports, screenshots, Motion Graphics templates, or packaged distribution for macOS and Windows.
Why use it?
They explain how the project is structured, how its delivery options differ, and what users need installed, helping an agent work on the integration and its operation pipeline correctly.

Instructions file for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is Engine-Room-Games/after-effects-mcp's own configuration. It tells Claude Code how to work on after-effects-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything after-effects-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Engine-Room-Games/after-effects-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Engine-Room-Games/after-effects-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Engine-Room-Games/after-effects-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for after-effects-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/engine-room-games/after-effects-mcp/claude-md.svg)](https://agentmods.dev/instructions/engine-room-games/after-effects-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/engine-room-games/after-effects-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/engine-room-games/after-effects-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 29,765 This file is loaded in full into every session.
When invoked 29,765 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.29765 $0.29765
Opus 5 $0.14882 $0.14882
Sonnet 5 $0.05953 $0.05953
Haiku 4.5 $0.02976 $0.02976

Measured 2d ago against content hash d2071d6e64e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

after-effects-mcp CLAUDE.md scanned grade C with 2 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

14. Missing dependency: `rm -rf …/games.engine-room.ae-mcp/node_modules/ws`, restart AE. The panel shows "cannot start — the ws module is missing" with the fix in its log, rather than "starting…". `check_setup` → `panelD

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

6. **Reload in AE** (optional, dev only) — `curl -X POST http://127.0.0.1:7777/reload-jsx` re-`$.evalFile`s the bundle without restarting AE.
CLAUDE.md · 771 lines

How it starts

The opening of the file, as written. The whole thing — 771 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude development guide — after-effects-mcp

This file is for future Claude Code sessions working in this repo. Humans reading it: see README.md for the user-facing intro.

What this project is

An MCP server that lets an LLM drive Adobe After Effects 2026: comps, layers, transforms, keyframes (with full interpolation/easing/tangent control), expressions, effects, text, shapes, masks, markers, footage import, audio cue placement, comp snapshots and diffs, Motion Graphics template export, one-off screenshots and contact sheets, bulk batches. 74 tools. macOS and Windows — the only two platforms AE runs on.

It ships five ways, and the ordering below is deliberate — it goes from least to most that the user has to already have installed:

For Needs
.mcpb bundle Claude Desktop nothing — Desktop runs it on the Node it ships
Signed binary any client, no Node download and unzip
npm package any client Node 22+
Claude Code plugin Claude Code this repo added as a marketplace
git checkout development the lot

Nothing here is Claude-only by design. Skills and slash commands exist only in Claude's clients, so anything written only there reaches maybe half the users. The cross-cutting knowledge is carried by the MCP instructions field, MCP prompts, MCP resources and the ae_guide tool — all four are generated from the same source, and the Claude Code skills are one more generated output rather than the original. See "Guidance and how it reaches an agent" below.

How the pieces talk

Claude / MCP client
        │ stdio (JSON-RPC)
        ▼
packages/mcp-server (Node/TS)
        │ HTTP POST /op  +  WS /events
        ▼  (127.0.0.1:7777)
packages/ae-panel (CEP extension, installed into AE)
        │ CSInterface.evalScript
        ▼
ExtendScript inside AE  (bundle.jsx = concat of packages/jsx/*.jsx)
        │ AE scripting API
        ▼
After Effects

The MCP server is stateless except for an in-memory JobManager, the SnapshotStore and the write queue. The panel is the only thing that talks to AE; it holds a Promise-chain mutex around evalScript because ExtendScript is single-threaded and concurrent calls would interleave. That mutex is necessary and not sufficient — see "Serializing writes" below.

Read the full file on GitHub · 771 lines

Changes

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.

  1. 2d ago Changed · +404 lines · +16,690 tokens per session d2071d6e64e0
  2. 8d ago First seen · 367 lines · 13,075 tokens per session scan C 8ccf0ece3e6b

Subscribe to this mod's changes

after-effects-mcp CLAUDE.md is an instructions file published in the GitHub repository Engine-Room-Games/after-effects-mcp (7 stars, last pushed 2d ago), licensed MIT. It adds 29,765 tokens to every session, about $0.1488 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens