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.
curl -O https://raw.githubusercontent.com/Engine-Room-Games/after-effects-mcp/main/CLAUDE.mdgit 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/instructions/engine-room-games/after-effects-mcp/claude-md)<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/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/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="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 | $0.05517 | $0.05517 |
| Opus 5.5 | $0.02207 | $0.02207 |
| Sonnet 5.5 | $0.01103 | $0.01103 |
| Haiku 4.5 | $0.00552 | $0.00552 |
Grade A, and why
after-effects-mcp CLAUDE.md scanned grade A with 1 finding 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.
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 -H "x-ae-mcp-token: $(cat ~/.engineroom-ae-mcp/token-7777)" http://127.0.0.1:7777/reload-jsx` re-`$.evalFile`s the bundle without restarting AE. The header is not How it starts
The opening of the file, as written. The whole thing — 221 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.
This file is the core, and it is loaded on every task. It holds what is
needed to orient and what silently produces wrong output if you do not know it.
Everything else — the measured traps, the subsystem reasoning, the live-AE
recipes — sits behind it in docs/, opened when a task reaches that subject.
The same split the guides use, for the same reason: prose resident in every
session is a tax on every request the user ever makes.
| Read | When |
|---|---|
docs/architecture.md |
The annotated source tree, and the op path in detail: the one op whose input is rewritten, cross-field rules, the special return shapes, write serialization. |
docs/subsystems.md |
Panel version gating, the project scaffold, the house style, comp snapshots, the issue journal. |
docs/guidance-system.md |
How agent guidance is written once and generated into every carrier. Read before touching anything under src/guides/ or src/prompts/. |
docs/fragile-areas-ae.md |
Measured After Effects and ExtendScript behaviour: undo, shapes, text, audio, mogrt, expressions, run_jsx. |
docs/fragile-areas-bridge.md |
The bridge, ports, CEP, the panel, and the screenshot pipeline. |
docs/fragile-areas-server.md |
Tool schemas and the MCP protocol, the journal's caches, packaging and binaries. |
docs/verification-recipes.md |
The 46 recipes run by hand against a live AE 2026. |
Nothing in docs/ is generated — hand-written, like this file. The generated
prose is elsewhere and is called out below.
Driving After Effects is not this file's subject. .mcp.json connects this
server to any session opened in the repo, so that guidance is already available
on demand: call ae_guide({topic}), or read the sources under
packages/mcp-server/src/guides/. The division is that the guides own how
After Effects behaves; docs/ owns why this code is shaped the way it is.
Where a fact belongs to both, the guide keeps the behaviour and the repo doc
keeps the reasoning and points at the topic — a second copy of the ease-arity
table is how that one went stale once already.
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 · +84 tokens per session cdc69f485390
- 1mo ago Changed · -550 lines · -24,332 tokens per session scan C → A 8c074fc3956b
- 1mo ago Changed · +404 lines · +16,690 tokens per session d2071d6e64e0
- 1mo ago First seen · 367 lines · 13,075 tokens per session scan C 8ccf0ece3e6b
after-effects-mcp CLAUDE.md is an instructions file published in the GitHub repository Engine-Room-Games/after-effects-mcp (37 stars, last pushed 3d ago), licensed MIT. It adds 5,517 tokens to every session, about $0.0221 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.