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.
git 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/create-style-guide)<a href="https://agentmods.dev/commands/engine-room-games/after-effects-mcp/create-style-guide"><img src="https://agentmods.dev/badge/commands/engine-room-games/after-effects-mcp/create-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/commands/engine-room-games/after-effects-mcp/create-style-guide"><img src="https://agentmods.dev/badge/commands/engine-room-games/after-effects-mcp/create-style-guide.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 | $0.00030 | $0.00419 |
| Opus 5.5 | $0.00012 | $0.00168 |
| Sonnet 5.5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
create-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 7d 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.
What it actually says
Set up the style guide
The user wants everything you build to look like their work rather than
generic motion graphics. That is what the style guide is for. It is saved as
house-style.md next to their After Effects project and read before every build.
$ARGUMENTS may name a comp to learn from.
Load the style-guide topic of ae_guide and follow it. In short:
get_house_stylefirst. If one exists, you are editing, not creating — read it, keep what is there, and send the whole merged document back.- Prefer reading the style off work they already like over asking them to
describe it. Ask which comp, then
get_compandget_layer_fullon the layers that carry the look, andanalyze_motionon the comps that move the way they like for the timing signature — eases, durations, overshoot, staggers. - Show what you found in plain language and let them correct it. Adjectives from you, numbers in the file.
- Only once they agree, write it with
set_house_style(overwrite: truewhen replacing), then tell them where it is and that they can edit it in any text editor.
Two things that will stop you: the project must have been saved at least
once, and set_house_style replaces the whole file rather than patching it.
If they have nothing to learn from, do not run a long interview. Ask four questions with concrete options, build one small example, screenshot it, and refine from their reaction — reacting is much 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.
- 7d ago Changed · +3 lines 39e42886c562
- 2mo ago First seen · 33 lines · 30 tokens per session scan A e56c175435fd
create-style-guide is a command published in the GitHub repository Engine-Room-Games/after-effects-mcp (45 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 419 once invoked, about $0.0001 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.
create-style-guide compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-style-guideEngine-Room-Games/after-effects-mcp | Command | 45 | 6d ago | MIT | A | 30 | Claude Code |
| openhop-flownaorsabag/openhop | Command | 48 | 3d ago | MIT | A | 35 | Claude Code |
| sheleg-designssheleg/sheleg-design-skill | Command | 4 | 4d ago | MIT | A | 16 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | today | MIT | A | 26 | Claude Code |