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-houdini --skill houdini-mesh-opsgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-houdiniWrote 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-houdini/houdini-mesh-ops)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-houdini/houdini-mesh-ops"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-houdini/houdini-mesh-ops/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-houdini/houdini-mesh-ops"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-houdini/houdini-mesh-ops.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 | $0.00073 | $0.00667 |
| Opus 5.5 | $0.00029 | $0.00267 |
| Sonnet 5.5 | $0.00015 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
houdini-mesh-ops 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.
What it actually says
houdini-mesh-ops
Typed modeling tools that build procedural SOP networks. Mutating tools use bounded inputs and return parameter plus cooked-geometry readback. A tool fails closed and removes its partial SOP when required native parameters, cooking, or postconditions cannot be verified; there is no raw-script fallback.
All tools are affinity: main (they call hou).
Tool group
mesh-edit(default active): the existing transform/merge/group/normal/ triangulate/convert tools;blast_geometryremains destructive.modeling(default inactive):loft_sections,lathe_profile,extrude_faces,bevel_edges,inset,bridge_edges,boolean_op,add_edge_loop,array_instances(bounded radial/tangentorientreadback before Copy to Points),mirror,auto_uv, anduv_project.
Tracer-bullet flow
houdini_geometry__create_primitive(parent_path="/obj/geo1", primitive="box")bevel_edges(input_path=".../box1", group="0-3", distance=0.05)array_instances(input_path=".../polybevel1", count=4, radius=3.5, axis="y")auto_uv(input_path=".../copytopoints1")houdini_geometry__get_cook_status(node_path=".../uvunwrap1")→ inspect again
blast_geometry is flagged destructive because it removes geometry; pass
delete_non_selected=true to invert the selection (keep the group).
Use houdini-object-ops.set_pivot for OBJ pivots and
houdini-materials.assign_material for material ownership. Houdini's procedural
SOP graph has no safe one-to-one delete_history operation; use the existing
explicit node-lock/export tools when a baked boundary is actually intended.
What ships with it
22 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 673 B
- scripts/_mesh_common.py 11 KB runs code
- scripts/add_edge_loop.py 2.5 KB runs code
- scripts/add_normals.py 1.7 KB runs code
- scripts/array_instances.py 12 KB runs code
- scripts/auto_uv.py 2.9 KB runs code
- scripts/bevel_edges.py 3.3 KB runs code
- scripts/blast_geometry.py 2.2 KB runs code
- scripts/boolean_op.py 3.0 KB runs code
- scripts/bridge_edges.py 3.1 KB runs code
- scripts/convert_geometry.py 2.0 KB runs code
- scripts/extrude_faces.py 4.0 KB runs code
- scripts/group_geometry.py 2.1 KB runs code
- scripts/inset.py 760 B runs code
- scripts/lathe_profile.py 3.4 KB runs code
- scripts/loft_sections.py 3.1 KB runs code
- scripts/merge_geometry.py 1.8 KB runs code
- scripts/mirror.py 3.3 KB runs code
- scripts/transform_geometry.py 2.0 KB runs code
- scripts/triangulate_geometry.py 1.6 KB runs code
- scripts/uv_project.py 3.5 KB runs code
- tools.yaml 21 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.
- 1mo ago First seen · 57 lines · 73 tokens per session scan A 07cb353e24ad
houdini-mesh-ops is a skill published in the GitHub repository dcc-mcp/dcc-mcp-houdini (19 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 667 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 2026-08-30.
Other skills, from other repositories
maya-mesh-ops
Authoring stage — typed polygon construction and editing: loft, lathe, instance arrays, pivots, mirror, combine, separate, and cleanup. Use for creating or modifying polygon topology from explicit scene inputs. Not for primitive creation (use maya-primitives), construction-history or DG inspection (use…
maya-primitives
Authoring stage — schema-validated quick path for creating polygon primitives and editing transforms. Use for predictable, agent-driven primitive creation; the parameters are validated by inputSchema and the results carry structured object names. For complex mesh editing use maya-mesh-ops, for materials use…
commercial-3d-product-render
Product lookdev and render-review helpers for commercial 3D work.
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.
designer-session
Host skill - inspect, author, save, and export a Substance 3D Designer graph. Use when an Agent needs bounded node, connection, parameter, gradient, output, package, resource, map, or SBSAR operations instead of arbitrary Python execution.
sd-node-ops
A Substance Designer guide for creating, connecting, and configuring nodes in material graphs, which are step-by-step networks that produce textures.