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/report-ae-issue)<a href="https://agentmods.dev/commands/engine-room-games/after-effects-mcp/report-ae-issue"><img src="https://agentmods.dev/badge/commands/engine-room-games/after-effects-mcp/report-ae-issue.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 | $0.00022 | $0.00952 |
| Opus 5 | $0.00011 | $0.00476 |
| Sonnet 5 | $0.00004 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
report-ae-issue 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 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.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report a problem with the After Effects tools
The user wants to tell the maintainers about something that did not work. They are most likely a motion designer, not a developer: they may never have seen GitHub, and they should not have to. Do the technical part yourself and only ask them things they can actually answer.
$ARGUMENTS is what they typed, if anything.
1. Find out what to report
Call list_known_issues with status: "unreported". It returns a one-line index
of what earlier sessions wrote down, plus repo, newIssueUrl, serverVersion
and platform. Once they have chosen, read each chosen entry in full with
list_known_issues({id}) — the draft below needs the symptom and workaround
text, which the index does not carry.
- Entries exist — show them as a short numbered list, one plain sentence each ("Text layers ended up in the wrong place when a font was missing"), not the raw titles. Ask which to send; offer "all of them" as an option.
- No entries, but
$ARGUMENTSdescribes something — work from that. Ask what they were trying to do and what happened instead, thenlog_issueit so it is recorded before you send it. - Nothing either way — say there is nothing recorded to send, and that you will write things down as you hit them from now on. Stop there.
2. Draft it
Short. A maintainer should understand the problem in fifteen seconds.
Title: one line, concrete. set_temporal_ease fails on Position with "Value array does not have 1 elements" — not Keyframe bug.
Body: four short sections, a couple of sentences each.
**What happens**
<the failing call and the exact error, or the wrong result>
**Why** (if known)
<one line — omit this section entirely if unknown>
**Workaround**
<what got past it>
**Environment**
after-effects-mcp <serverVersion> · <platform> · After Effects 2026
Include the failing call and error text verbatim — that is the part that makes it fixable. Leave out the user's own content: comp and layer names from their project, file paths, client names, anything about the video they are making. If a detail like that is load-bearing, replace it with a placeholder.
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.
- 2d ago Changed · +3 lines bc70ec1c8b9b
- 8d ago First seen · 91 lines · 22 tokens per session scan A 4cd284f34de7
report-ae-issue is a command published in the GitHub repository Engine-Room-Games/after-effects-mcp (7 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 952 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.