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 agentmods add skills/dcc-mcp/dcc-mcp-core/example-layered-skillnpx skills add dcc-mcp/dcc-mcp-core --skill example-layered-skillgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-coreWrote 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-core/example-layered-skill)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-core/example-layered-skill"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-core/example-layered-skill.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00703 |
| Opus 5 | $0.00035 | $0.00351 |
| Sonnet 5 | $0.00014 | $0.00141 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
example-layered-skill 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 6d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layered Skill Architecture — Reference
This skill demonstrates the internal layered organisation recommended for
complex skills (see docs/guide/skills.md
section "Complex Skill Architecture").
It is intentionally simple — three asset-management tools that share a small service object — so the structure, not the business logic, is the focus.
Layout
example-layered-skill/
├── SKILL.md ← this file (frontmatter + prose)
├── tools.yaml ← MCP tool declarations (sibling, per #356)
├── scripts/
│ ├── __init__.py
│ ├── create_asset.py ← thin tool adapters (parse params, return envelope)
│ ├── publish_asset.py
│ ├── validate_asset.py
│ ├── services/ ← business logic (orchestration, error handling)
│ │ ├── __init__.py
│ │ └── asset_service.py
│ └── utils/ ← pure helpers (no I/O, no DCC calls, fully unit-testable)
│ ├── __init__.py
│ └── path_utils.py
└── prompts/
└── system.md ← optional system prompt sidecar
Layer responsibilities
| Layer | Responsibility | Size guidance |
|---|---|---|
| tool scripts | Parse JSON params from stdin, validate, delegate, return envelope. | < 30 lines |
| services/ | Orchestrate DCC commands. Easily unit-testable in isolation. | Grows with feature |
| utils/ | Pure functions — path normalisation, primitive helpers. No side effects. | Grows with feature |
Tools exposed
| Tool | Description |
|---|---|
example_layered_skill__create_asset |
Create a new asset record |
example_layered_skill__publish_asset |
Publish an existing asset |
example_layered_skill__validate_asset |
Validate an asset against project rules (read-only) |
Why a sibling tools.yaml
Per #356, tool
declarations live in a sibling YAML referenced from
metadata.dcc-mcp.tools so that SKILL.md frontmatter stays
agentskills.io 1.0 compliant.
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.
- prompts/system.md 619 B
- scripts/__init__.py 78 B runs code
- scripts/create_asset.py 1.4 KB runs code
- scripts/publish_asset.py 1.1 KB runs code
- scripts/services/__init__.py 54 B runs code
- scripts/services/asset_service.py 2.1 KB runs code
- scripts/utils/__init__.py 76 B runs code
- scripts/utils/path_utils.py 700 B runs code
- scripts/validate_asset.py 1.1 KB runs code
- tools.yaml 1.7 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.
- 6d ago First seen · 75 lines · 70 tokens per session scan A 600adfeac88e
example-layered-skill is a skill published in the GitHub repository dcc-mcp/dcc-mcp-core (42 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 703 once invoked, about $0.0003 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
artclaw-tool-creator
ArtClaw Tool Creator - AI 引导创建自定义 DCC 工具。支持三种创建方式：包装 Skill、编写脚本、组合工具。.
sd-node-ops
SD 节点创建、连接、参数设置指南。包含原子节点和库节点的正确使用方式。 Use when AI needs to: (1) create nodes, (2) connect nodes, (3) set parameters, (4) build material graphs. Substance Designer only (runpython).
houdini-simulation
Houdini 仿真工作流指南：Pyro/RBD/FLIP/Vellum 的标准搭建流程。 Use when AI needs to: (1) set up simulations, (2) configure DOPs, (3) build Pyro/RBD/FLIP/Vellum setups. Houdini only (runpython).
blender-context
查询 Blender 编辑器上下文：当前选择、场景信息、文件名、视口相机状态、集合结构。 Use when AI needs to: (1) get selected objects, (2) get scene overview, (3) check current file, (4) inspect viewport state, (5) get collection hierarchy. Blender only (runpython).
blender-viewport-capture
捕获 Blender 视口截图用于 AI 分析。支持 OpenGL 渲染截图和渲染预览截图。 Use when AI needs to: (1) take a screenshot of the current viewport, (2) analyze scene composition visually, (3) capture rendered preview for AI feedback. NOT for: final production rendering, animation rendering. Blender only (runpython).
comfyui-img2img
ComfyUI 图生图工作流构建与执行。 Use when AI needs to: (1) generate image from another image, (2) perform image-to-image transformation, (3) apply style transfer or enhancement to existing image. ComfyUI only (runpython).