agentmods.dev

dcc-mcp-houdini: Skill for Claude Code

.cursor/skills/dcc-mcp-skill-developer/SKILL.md

dcc-mcp-skill-developer is a skill for Claude Code, Cursor from dcc-mcp/dcc-mcp-houdini. It costs 106 tokens per session (829 once invoked), scanned A, original, MIT.

A guide for building and changing adapter packages that let coding agents work with creative software such as Maya, Blender, 3ds Max, Houdini, Photoshop, ZBrush, Unreal, and Unity. It covers the package instructions, tools, server wiring, and tests.

In plain words
What is it for?
Use it to create or update a host adapter, add a domain skill, port an integration to another creative application, and test its local or REST-based behavior.
Why use it?
It provides shared patterns for adding new software integrations without overlooking tool declarations, safety details, discovery, or testing.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: allowed-tools in frontmatter, but also installed under .cursor/.

This is dcc-mcp/dcc-mcp-houdini's own configuration. It tells Claude Code and Cursor how to work on dcc-mcp-houdini itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dcc-mcp-houdini configures →

not rated 12repo +1 today A scan 106 tokens original MIT
View source ↗ dcc-mcp/dcc-mcp-houdini pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to dcc-mcp/dcc-mcp-houdini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dcc-mcp/dcc-mcp-houdini/main/.cursor/skills/dcc-mcp-skill-developer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-houdini

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for dcc-mcp-skill-developer

README.md
[![agentmods](https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-houdini/dcc-mcp-skill-developer/github.svg)](https://agentmods.dev/skills/dcc-mcp/dcc-mcp-houdini/dcc-mcp-skill-developer)
Your own site
<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-houdini/dcc-mcp-skill-developer"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-houdini/dcc-mcp-skill-developer/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.

agentmods 80×15 button for dcc-mcp-skill-developer

Your own site · 80×15
<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-houdini/dcc-mcp-skill-developer"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-houdini/dcc-mcp-skill-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 829 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.00829
Opus 5 $0.00053 $0.00415
Sonnet 5 $0.00021 $0.00166
Haiku 4.5 $0.00011 $0.00083

Measured 10d ago against content hash b13d40aad7e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dcc-mcp-skill-developer 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.

.cursor/skills/dcc-mcp-skill-developer/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DCC-MCP Skill Developer

Use this skill when you are changing or creating DCC-MCP adapter skill packages. It distills patterns from dcc-mcp-maya, dcc-mcp-blender, and dcc-mcp-3dsmax into a faster authoring loop.

Fast Workflow

  1. Classify the work: new host adapter, new domain skill, new infrastructure skill, or porting an existing skill to another DCC.
  2. Read only the reference you need:
  3. Prefer existing adapter helpers before adding new abstractions.
  4. Keep DCC identity parameterized: dcc_name, dcc_type, environment prefixes, skill names, and search examples.
  5. Make every tool declaration explicit: source_file, execution, affinity, safety annotations, and timeout_hint_secs for async tools.
  6. Add tests at the lowest executable layer, then one discovery/load/call or gateway REST path when behavior crosses MCP or REST boundaries.

Adapter Selection

  • Use Maya patterns for mature stage taxonomy, main-thread dispatch, cancellation, resources, readiness, capability manifests, and strict skill linting.
  • Use Blender patterns for a lean DccServerBase adapter scaffold and progressive loading helpers.
  • Treat current 3ds Max skills as migration targets: preserve the pymxs domain logic, but modernize into nested SKILL.md, tools.yaml, and scripts.
  • For future hosts, start from Blender's lean scaffold, then add Maya-style lifecycle hardening only when the host actually needs it.

Non-Negotiables

  • No top-level dcc-mcp extension keys in SKILL.md.
  • No host API imports at module import time in skill scripts.
  • No scene-touching tool without affinity: main.
  • No execution: async without a realistic timeout_hint_secs.
  • No new generic helper crate or module when core or an adapter-local owner already exists.
  • No raw execute_python or execute_mel as the primary UX when a typed tool can exist.

Read the full file on GitHub · 75 lines

Files

What ships with it

4 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.

Changes

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.

  1. 10d ago First seen · 75 lines · 106 tokens per session scan A b13d40aad7e3

Subscribe to this mod's changes

dcc-mcp-skill-developer is a skill published in the GitHub repository dcc-mcp/dcc-mcp-houdini (12 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 829 once invoked, about $0.0005 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.

Building agentsCreative and mediaai-agentsdcchoudinimcpmodel-context-protocolprocedural-generation
Related

Other skills, from other repositories

maya-render

Pipeline stage — render globals, final-frame rendering, and viewport capture: configure render settings, query them, render frames, capture playblasts. Use for producing final or preview imagery. Not for modeling (maya-mesh-ops), animation editing (maya-animation), generic file import/export (maya-geometry), or render…

dcc-mcp/dcc-mcp-maya · 77 tokens

maya-scripting

Bootstrap stage — escape hatch for Maya work that has no packaged skill yet. Agents should prefer searchskills / dcccapabilitymanifest → loadskill → typed tools (inputSchema + annotations) from domain skills; use executepython or executemel only when no skill matches, for bulk in-process loops, or for API…

dcc-mcp/dcc-mcp-maya · 100 tokens

dcc-mcp-core

Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…

dcc-mcp/dcc-mcp-core · 109 tokens

dcc-mcp-maya-setup

Set up dcc-mcp-maya for an agent or operator: install Maya Python dependencies with mayapy, generate MCP host configuration, guide the user through loading the Maya plugin, and run a first live-tool smoke prompt.

dcc-mcp/dcc-mcp-maya · 55 tokens

maya-asset-source

Pipeline stage — asset discovery and resolution. Search local asset libraries, resolve paths to structured AssetDescriptor records, and surface candidate assets for downstream import. Use before maya-import-to-scene to locate what to import.

dcc-mcp/dcc-mcp-maya · 50 tokens

maya-pipeline

Domain skill — Maya asset pipeline orchestration: set up project directory structures, export scenes to USD, and coordinate multi-step DCC workflows. Use when initialising a Maya project or exporting assets for a downstream pipeline. Not for raw geometry editing — use maya-geometry for that. Not for low-level USD file…

dcc-mcp/dcc-mcp-core · 74 tokens