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.
npx skills add abrahamADSK/maya-mcp --skill maya-scene-assemblygit clone --depth 1 https://github.com/abrahamADSK/maya-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/abrahamadsk/maya-mcp/maya-scene-assembly)<a href="https://agentmods.dev/skills/abrahamadsk/maya-mcp/maya-scene-assembly"><img src="https://agentmods.dev/badge/skills/abrahamadsk/maya-mcp/maya-scene-assembly/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/abrahamadsk/maya-mcp/maya-scene-assembly"><img src="https://agentmods.dev/badge/skills/abrahamadsk/maya-mcp/maya-scene-assembly.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 | $0.01412 |
| Opus 5.5 | $0.00035 | $0.00565 |
| Sonnet 5.5 | $0.00017 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
maya-scene-assembly 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 8d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scene assembly from references
Applies to any production Maya scene whose contents come from other published files — shots, layout, set dressing, character loading. The failure modes here were paid for in-vivo; none of them raise an error when they happen.
For which cmds.file flag to use, ask search_maya_docs. This skill is the
order of operations and what corrupts a scene quietly.
1. The deferred-reference save trap
This is the one that costs real work.
A reference can sit in a scene unloaded (deferred) — present in the structure, absent from memory. Artists keep heavy scenes workable that way on purpose.
Opening that scene by script can pull those references into memory. If you then save, you have baked them in, and handed back a scene that is heavier than the one the artist built and no longer matches their intent.
The rule:
- After any scripted open, check reference load state before you save, and unload whatever was unloaded when you found it.
- Better: do not save at all unless saving is the point of the task. A read operation that ends in a save is a bug, not a convenience.
2. Reference or import?
maya_import_file imports: the geometry becomes part of your scene
permanently, with no link back to the source. Right for one-off geometry, mocap,
and generated assets (Vision3D / WorldLabs output).
A reference keeps the link, so upstream republishes can flow in. Right for anything a pipeline publishes — characters in shots, sets, layout, props.
The test is one question: will somebody republish this upstream? If yes, it must be a reference. Importing it instead severs the shot from the asset, and nobody notices until the character changes and the shot doesn't.
Note that maya-mcp's own demo history is import-heavy. That was a toy-scene artefact, not a pattern to copy.
3. Use the dedicated tool
maya_reference is the route. Five operations:
| operation | does | needs |
|---|---|---|
create |
references the file in, namespaced | file_path, optional namespace |
list |
every reference node + file + namespace + loaded state | — |
replace |
repoints a node at a new file (the version swap) | reference_node, file_path |
load / unload |
drops or restores content, keeping the link | reference_node |
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.
- 8d ago First seen · 126 lines · 87 tokens per session scan A 39f9c21913e3
maya-scene-assembly is a skill published in the GitHub repository abrahamADSK/maya-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 1,412 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 2026-09-29.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…