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 IvanYangYangXi/artclaw_bridge --skill blender-material-opsgit clone --depth 1 https://github.com/IvanYangYangXi/artclaw_bridgeWrote 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/ivanyangyangxi/artclaw_bridge/blender-material-ops)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/blender-material-ops"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/blender-material-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/ivanyangyangxi/artclaw_bridge/blender-material-ops"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/blender-material-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 | $0.00085 | $0.02221 |
| Opus 5.5 | $0.00034 | $0.00888 |
| Sonnet 5.5 | $0.00017 | $0.00444 |
| Haiku 4.5 | $0.00009 | $0.00222 |
Grade A, and why
blender-material-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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender 材质操作指南
强制规则:
- 用
node.type查找节点(不用node.name,中文版名字不同)- 创建材质后必须验证节点数和颜色值
bpy.data.materials.new()会自动创建默认 BSDF+Output,不要再 new 一对- 需要重建节点时,先
nodes.clear()再 new
规则 0:use_nodes=True 的隐含行为 🔴
mat = bpy.data.materials.new(name="MyMat")
mat.use_nodes = True
# 此时 mat.node_tree.nodes 已包含:
# - 1 个 Principled BSDF (type='BSDF_PRINCIPLED')
# - 1 个 Material Output (type='OUTPUT_MATERIAL')
# - 1 条 BSDF→Output 连接
# 不需要也不能再 nodes.new() 同类型节点!
❌ 典型错误(重复节点,材质变灰)
mat = bpy.data.materials.new(name="Wall")
mat.use_nodes = True
# 已经有默认节点了!下面又创建一对 → 总共 4 个节点
bsdf = mat.node_tree.nodes.new('ShaderNodeBsdfPrincipled') # 重复!
output = mat.node_tree.nodes.new('ShaderNodeOutputMaterial') # 重复!
# 新 BSDF 没连到 Output,材质显示为灰色
模式 A:创建新材质(最常用)
直接使用 use_nodes=True 创建的默认节点,只修改参数:
mat = bpy.data.materials.new(name="Wall_Material")
mat.use_nodes = True
tree = mat.node_tree
# 通过 type 查找默认节点(兼容中英文 Blender)
bsdf = None
output = None
for node in tree.nodes:
if node.type == 'BSDF_PRINCIPLED':
bsdf = node
elif node.type == 'OUTPUT_MATERIAL':
output = node
# 设置参数
bsdf.inputs['Base Color'].default_value = (0.9, 0.85, 0.75, 1.0)
bsdf.inputs['Roughness'].default_value = 0.8
bsdf.inputs['Metallic'].default_value = 0.0
# 验证
assert len(tree.nodes) == 2, f"节点数异常: {len(tree.nodes)}"
assert len(tree.links) == 1, f"连接数异常: {len(tree.links)}"
模式 B:修改已有材质
只改参数,不碰节点结构:
mat = bpy.data.materials.get("Wall_Material")
if mat and mat.use_nodes:
for node in mat.node_tree.nodes:
if node.type == 'BSDF_PRINCIPLED':
node.inputs['Base Color'].default_value = (0.95, 0.9, 0.8, 1.0)
node.inputs['Roughness'].default_value = 0.7
break
模式 C:重建损坏的材质
先清除再创建——材质有重复节点或连接断开时使用:
mat = bpy.data.materials.get("Wall_Material")
if not mat:
mat = bpy.data.materials.new(name="Wall_Material")
mat.use_nodes = True
tree = mat.node_tree
# 清除所有节点(关键步骤)
tree.nodes.clear()
# 重新创建
bsdf = tree.nodes.new(type='ShaderNodeBsdfPrincipled')
bsdf.location = (0, 0)
bsdf.inputs['Base Color'].default_value = (0.9, 0.85, 0.75, 1.0)
bsdf.inputs['Roughness'].default_value = 0.8
output = tree.nodes.new(type='ShaderNodeOutputMaterial')
output.location = (300, 0)
tree.links.new(bsdf.outputs['BSDF'], output.inputs['Surface'])
# 验证
assert len(tree.nodes) == 2
assert len(tree.links) == 1
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 · 256 lines · 85 tokens per session scan A bd95a03d2ad5
blender-material-ops is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (36 stars, last pushed 6mo ago), licensed MIT. It adds 85 tokens to every session and 2,221 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
commercial-3d-product-render
Product lookdev and render-review helpers for commercial 3D work.
dcc-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
mesh-ops
Cross-adapter polygon modeling recipe pack for the shared cross-DCC modeling vocabulary. Structured RECIPES.yaml entries for primitive creation, hard-surface edits, topology cleanup, UV generation, radial arraying, and material assignment. Reusable by every DCC adapter's mesh-ops skill (maya, blender, houdini, 3dsmax…
example-layered-skill
Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…
marketplace-create-extension
Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.