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-rigginggit 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-rigging)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-maya/maya-rigging"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-maya/maya-rigging/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-rigging"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-maya/maya-rigging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.00630 |
| Opus 5 | $0.00039 | $0.00315 |
| Sonnet 5 | $0.00016 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
maya-rigging 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 10d 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.
What it actually says
maya-rigging (Authoring stage)
Joint hierarchies, IK handles, constraints, skin clusters, skin-weight transfer, deformers, blend shapes, optional rig framework detection, control curves, and editable hair guide curves. Twenty-one scripts cover the typical rigging loop.
get_skin_weights reads an explicit bounded vertex subset (or the whole mesh
when it fits the limit) and reports per-vertex totals plus an
unnormalized_vertices count. It never silently truncates a large mesh.
set_skin_weights accepts only complete normalized rows for known influences,
clears omitted influence values on those vertices, and verifies every effective
native value before reporting success.
export_rig_state deterministically reports bounded joint hierarchy,
constraints, NURBS controls, and per-skin normalization health. Large rigs fail
closed instead of returning a partial snapshot.
create_guide_curve is the bounded guide-authoring contract: every open curve
has one cluster ID, one solid RGB viewport color, root-to-tip CV order, arc
length and cluster-median deviation metrics, and an optional measured root
projection distance against an explicit scalp mesh. It accepts only named
metadata fields (source_view and dominant_clump), never arbitrary script or
metadata payloads. The general-purpose create_curve contract remains
unchanged.
Optional Frameworks
Use detect_rig_frameworks before relying on optional packages such as mGear,
AdvancedSkeleton, MGTools, Go Skinning, Skin Magic, SI Weight Editor, or
MetaHuman-style DNA tools. Built-in rigging tools remain the default path; optional
frameworks are only used when detection reports available=true.
What ships with it
23 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 560 B
- scripts/assign_deformer.py 4.0 KB runs code
- scripts/blend_shape_add_target.py 2.9 KB runs code
- scripts/copy_skin_weights.py 4.0 KB runs code
- scripts/create_blend_shape.py 2.4 KB runs code
- scripts/create_constraint.py 3.3 KB runs code
- scripts/create_curve.py 2.6 KB runs code
- scripts/create_guide_curve.py 13 KB runs code
- scripts/create_ik_handle.py 2.5 KB runs code
- scripts/create_joint.py 2.6 KB runs code
- scripts/create_rig_control.py 7.2 KB runs code
- scripts/detect_rig_frameworks.py 5.0 KB runs code
- scripts/export_rig_state.py 10 KB runs code
- scripts/get_skin_weights.py 6.4 KB runs code
- scripts/mirror_joints.py 3.0 KB runs code
- scripts/query_skin_cluster.py 2.4 KB runs code
- scripts/set_driven_key.py 4.1 KB runs code
- scripts/set_ik_fk_blend.py 2.6 KB runs code
- scripts/set_joint_limit.py 3.7 KB runs code
- scripts/set_joint_orient.py 2.5 KB runs code
- scripts/set_skin_weights.py 10 KB runs code
- scripts/skin_cluster_bind.py 2.8 KB runs code
- tools.yaml 28 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.
- 10d ago First seen · 67 lines · 78 tokens per session scan A c3f185115259
maya-rigging is a skill published in the GitHub repository dcc-mcp/dcc-mcp-maya (53 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 630 once invoked, about $0.0004 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 2026-08-30.
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.
houdini-gsplat-relighting
Houdini 22 Gaussian Splat relighting skill - prepare GSplats with SideFX Labs, relight them in Solaris/Karma, and rasterize them in Copernicus. Use when an agent must relight a captured splat while retaining typed scene and parameter control. Not for training or importing a new Gaussian Splat.
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-lookdev
Domain skill - configure OCIO color management, HDR environment lighting, preview materials, and assign renderer-specific materials (Arnold, V-Ray, Scanline) in 3ds Max.
3dsmax-rigging
Domain skill - create and inspect host-native 3ds Max rig helpers, bones, constraints, controls, poses, native Skin weights, and common deformers.
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.