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/absorb-release)<a href="https://agentmods.dev/commands/engine-room-games/after-effects-mcp/absorb-release"><img src="https://agentmods.dev/badge/commands/engine-room-games/after-effects-mcp/absorb-release/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/absorb-release"><img src="https://agentmods.dev/badge/commands/engine-room-games/after-effects-mcp/absorb-release.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 | $0.00051 | $0.01403 |
| Opus 5.5 | $0.00020 | $0.00561 |
| Sonnet 5.5 | $0.00010 | $0.00281 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
absorb-release 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 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.
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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Absorb a tools update
The After Effects tools have updated, or the user thinks they have. A release changes what the tools do, and what earlier sessions wrote down about them in this project — workarounds in AGENTS.md or CLAUDE.md, entries in the issue journal — does not update itself. This flow reads the delta once, corrects those notes, and records the version so no later session reads the history again.
$ARGUMENTS is the version the project last absorbed, if the user typed one.
When to run this
At the start of a session, compare two versions:
- Recorded: the line
Tools version last absorbed: <version>in the project's docs.init_projectwrites it into AGENTS.md. - Running: the server's own version.
list_known_issuesreturns it asserverVersion, and everyae_guide({topic: "whats-new"})answer opens with it.
Running newer than recorded, or no recorded line at all, is the cue. Two things
update separately, so there can be two versions to look at: the MCP server (via
npx, the standalone binary, or the Claude Desktop bundle) and, in Claude Code,
the plugin that carries the skills and this command, whose version is in its
.claude-plugin/plugin.json. The server's version is the one this flow
records, because the server is what answers tool calls and what serves the
whats-new topic. If the plugin is ahead of the server, the skill text may
describe tools the server does not have yet — say so, and suggest updating the
server rather than the notes.
1. Find the recorded version
Look for Tools version last absorbed: in AGENTS.md, then CLAUDE.md,
.cursor/rules/, .windsurfrules, .github/copilot-instructions.md and any
notes under .ae-mcp/. $ARGUMENTS overrides whatever is found.
Nothing recorded and nothing typed: ask whether these tools have been used in this project before. If they have, treat it as never absorbed and read the whole history — one long read, once. If the project is new, there is nothing to absorb: go to step 5 and just record the version.
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 First seen · 122 lines · 51 tokens per session scan A e496f1ec0950
absorb-release is a command published in the GitHub repository Engine-Room-Games/after-effects-mcp (32 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 1,403 once invoked, about $0.0002 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 2026-09-09.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
r
Resume the last handoff and carry on with the outstanding work.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.
crear-skill
Crear, probar y mejorar skills de forma iterativa. Usa cuando el usuario dice "crear skill", "crear habilidad", "build skill", "create a skill", "skill development", "desarrollar skill", "nueva habilidad". Usa el workflow: draft → test → review → improve → repeat con evaluación cuantitativa y qualitative review.