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/skills/orchestrate/SKILL.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/skills/engine-room-games/after-effects-mcp/orchestrate)<a href="https://agentmods.dev/skills/engine-room-games/after-effects-mcp/orchestrate"><img src="https://agentmods.dev/badge/skills/engine-room-games/after-effects-mcp/orchestrate/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/skills/engine-room-games/after-effects-mcp/orchestrate"><img src="https://agentmods.dev/badge/skills/engine-room-games/after-effects-mcp/orchestrate.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 | $0.00087 | $0.02330 |
| Opus 5.5 | $0.00035 | $0.00932 |
| Sonnet 5.5 | $0.00017 | $0.00466 |
| Haiku 4.5 | $0.00009 | $0.00233 |
Grade A, and why
orchestrate 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrating work in after-effects-mcp
The maintainer's rule, verbatim: "Orchestration means you keep your context window as slim as possible and manage sub-agents (Opus) for everything. They research, implement, review (adversary review). When a feature is finished, tested and reviewed, you are responsible for merges."
Your role
- Do not read big files or diffs yourself. No
gh pr diff, no source dumps. If you need to know something, an agent finds out and tells you. - Hold only short reports. End every brief with: "Report in ≤150 words: what changed, PR URL, test result, anything you could not verify."
- Track state in a short list: issue → branch → PR → review → live check → merged.
model: "opus"for every agent. Launch independent agents in one message so they run in parallel.- Keep what you depend on. Agents may be refused writing report files, and
scratch space gets cleaned. Have agents return findings in their reply, and
save each findings/verdict file you need yourself in
~/.engineroom-ae-mcp-orchestrate/<date>/— outside the repo, and never in agent scratchpads,$TMPDIRor worktrees, which get cleaned. - Every agent that cleans up deletes only what it created. Brief it to record each file, folder, worktree and project it makes, and delete only those — never a folder because it looks like scratch. One cleanup deleted the reviewers' findings and a shared worktree.
1. Implement — one issue, one branch, one agent
Agent tool, isolation: "worktree", model: "opus". Worktrees are cut from
main; say so if the work depends on an unmerged branch. The brief is the only
context the agent gets, so make it self-contained:
- the issue number (
gh issue view N) and the outcome wanted; - read
CLAUDE.md, plus thedocs/*.mdfor the subject (the table at the top ofCLAUDE.mdsays which); - branch
fix/N-short-name(orfeat/,chore/) fromorigin/main; npm run buildandnpm testmust pass; add or extend atests/unit/test that fails without the fix;- commit with the attribution trailer from the session's system reminder;
- push and open a PR against
mainwhose body saysCloses #N; - never merge, never release, never edit
CLAUDE.mdor settings; - list anything that needs live After Effects to confirm.
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 · +54 lines 22e929997b87
- 8d ago First seen · 101 lines · 87 tokens per session scan A 99ecaa9e3ed8
orchestrate is a skill published in the GitHub repository Engine-Room-Games/after-effects-mcp (45 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 2,330 once invoked, about $0.0003 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 2026-10-29.
orchestrate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| orchestrateEngine-Room-Games/after-effects-mcp | Skill | 45 | 6d ago | MIT | A | 87 | Claude Code |
| commitalphacornutum/layercake | Skill | 0 | 18d ago | MIT | A | 100 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| git-commitThinkInAIXYZ/deepchat | Skill | 6.4k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| repo-syncdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 25 | Claude Code, Codex |
| mcore-split-prNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 25 | Claude Code |
| git-commit-writermergisi/awesome-openclaw-agents | Skill | 4.1k | 3d ago | MIT | A | 53 | Claude Code, Codex |