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 dcc-mcp/dcc-mcp-maya --skill maya-compositinggit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-mayaWrote 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/dcc-mcp/dcc-mcp-maya/maya-compositing)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-maya/maya-compositing"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-maya/maya-compositing/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/dcc-mcp/dcc-mcp-maya/maya-compositing"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-maya/maya-compositing.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 | $0.00129 | $0.01034 |
| Opus 5.5 | $0.00052 | $0.00414 |
| Sonnet 5.5 | $0.00026 | $0.00207 |
| Haiku 4.5 | $0.00013 | $0.00103 |
Grade A, and why
maya-compositing 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 23d 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.
maya-compositing (Pipeline stage)
Builds the shading/utility node network that combines already-rendered
imagery inside Maya, so a comp can be reviewed or rendered without leaving the
scene. It is the companion to render_setup.plan_comp_outputs, which decides
where those images land on disk.
Typical flow
create_image_reader— one per image sequence. Setuse_frame_extension=Trueforname.####.exrsequences, andframe_offsetwhen the render starts at a non-zero frame.create_layer_stack— an emptylayeredTextureto stack into.add_comp_layer— connect each reader, choosingblend_modeandopacity.list_comp_layers— verify order, modes and opacity before rendering.merge_comp_layers— shortcut for two sources:blendgives a uniform mix viablender, the other operations stack with the matching blend mode.create_comp_node+connect_comp_nodes— insertreverse,multiplyDivide,luminance,clamporsetRangefor keys and grades.
Verified Maya behaviours
Three things are easy to get wrong and invisible under a mock (all verified on Maya 2025):
layeredTexture.inputsreportssize == 0viagetAttr(s=True)before the first connection, andlistConnections(..., plugs=True)on the array returns the source plugs (f1.outColor), not the destination elements. Neither reveals an index, so the layer index comes from probing each element - and that also lets a removed layer's slot be reused.gradeandcolorCorrectexist as node types butcreateNodereturns anunknownnode in a batch session, so they are not offered.file.imageNamedoes not exist; onlyfileTextureNameis settable.
Input plugs differ per node type: multiplyDivide uses input1/input2,
plusMinusAverage uses input3D, and reverse/clamp use a plain input.
Scope
This skill builds comp networks. It does not render or plan paths:
- where renders land →
render_setup.plan_comp_outputs(maya-render-setup) - render layers, AOVs →
maya-render-setup - rendering frames →
maya-render/maya-render-farm
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- groups.yaml 642 B
- scripts/add_comp_layer.py 1.9 KB runs code
- scripts/connect_comp_nodes.py 1.7 KB runs code
- scripts/create_comp_node.py 1.7 KB runs code
- scripts/create_image_reader.py 1.9 KB runs code
- scripts/create_layer_stack.py 1.4 KB runs code
- scripts/list_comp_layers.py 1.5 KB runs code
- scripts/merge_comp_layers.py 1.9 KB runs code
- scripts/remove_comp_layer.py 1.6 KB runs code
- tools.yaml 4.5 KB
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.
- 23d ago First seen · 94 lines · 129 tokens per session scan A d2e2de2c1506
maya-compositing is a skill published in the GitHub repository dcc-mcp/dcc-mcp-maya (60 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 1,034 once invoked, about $0.0005 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 2026-09-23.
Other skills, from other repositories
dcc-mcp-3dsmax-setup
Set up dcc-mcp-3dsmax for an agent or operator: install 3ds Max Python dependencies with 3dsmaxpy, generate MCP host configuration, guide the user through starting the runtime inside 3ds Max, and run a first live-tool smoke prompt.
3dsmax-asset-source
Domain skill — search and resolve assets into validated AssetDescriptor contracts for cross-DCC asset import pipelines. Returns static catalog entries; production sources can layer download helpers or remote resolution without changing the contract.
3dsmax-scene
Domain skill - open, save, merge, inspect, and manage scenes and objects in the current Autodesk 3ds Max session. Use for typed scene lifecycle, nodes, cameras, selection, visibility, parenting, grouping, pivots, transforms, scene metadata, or object cleanup.
3dsmax-mesh-ops
Domain skill - inspect and mutate 3ds Max mesh topology, cleanup, smoothing groups, modifier stacks, proxy meshes, explicit normals, and native boolean solids through atomic host-native operations.
3dsmax-camera-lighting
Domain skill - create, inspect, and adjust 3ds Max cameras, lights, and simple review lighting rigs.
3dsmax-modeling
Domain skill - create basic primitives, bounded native Lathe geometry, splines and curve models, and lofted surfaces on the 3ds Max main thread. Use when adding boxes, spheres, cylinders, planes, a rotational form from a typed profile, a spline drawn from world-space points, a named parametric curve model, or a loft…