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-blender --skill blender-uv-opsgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-blenderWrote 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-blender/blender-uv-ops)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-blender/blender-uv-ops"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/blender-uv-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-blender/blender-uv-ops"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/blender-uv-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 | $0.00057 | $0.00811 |
| Opus 5 | $0.00028 | $0.00405 |
| Sonnet 5 | $0.00011 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
blender-uv-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 yesterday.
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
blender-uv-ops
Typed UV authoring tools for Blender meshes. Load this skill when a workflow needs UV maps, texture-coordinate projection, unwraps, UV island diagnostics, packing, or normalization.
Prefer blender-mesh for topology and modifier work, blender-materials for
material slots, and blender-shader-nodes for shader graph edits. Use
blender-scripting only after checking this typed surface.
Quality and delivery
Use audit_uv_layout with explicit mesh names (up to 4096) for source mesh
quality checks. It does not evaluate modifiers or silently switch out of Edit
Mode. success means the query ran; require both context.complete and
context.passed for a clean result for the enabled checks (reported in
context.checks); disabling overlap is not a complete quality acceptance.
Budget limits are shared by the entire
request; complete=false requires a narrower request or a larger budget.
Counts for degeneracy, tile bounds and overlap are triangle counts/pairs,
not unique polygons. Face indices in the bounded detail list locate problems.
per_object overlap is the default; choose selection only when those objects
must share a non-overlapping atlas. Exact coincident triangle stacks (including
mirrors) are allowed only with allow_stacked=true. UV distortion and texel
density are not measured. udim permits tile crossings and validates only the
nonnegative ten-column coordinate domain, not texture-file availability.
Use export_uv_layout to write actual polygon UV edges to a new SVG path.
Each object gets its own labelled panel, fitted to its coordinates with the
unit-tile border shown; panels do not imply shared texel scale. Export is a
layout visualization, not a quality pass. It neither packs nor repairs UVs.
The default panels mode accepts at most 64 objects. Choose layout_mode=overlay
to display up to 4096 objects in their shared UV coordinate space. Set an
explicit max_triangles budget (up to 500000) for larger atlas exports.
What ships with it
13 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.
- scripts/audit_uv_layout.py 370 B runs code
- scripts/copy_uv_map.py 411 B runs code
- scripts/create_uv_map.py 409 B runs code
- scripts/delete_uv_map.py 411 B runs code
- scripts/export_uv_layout.py 372 B runs code
- scripts/get_uv_info.py 406 B runs code
- scripts/get_uv_islands.py 421 B runs code
- scripts/list_uv_maps.py 403 B runs code
- scripts/normalize_uvs.py 419 B runs code
- scripts/pack_uvs.py 395 B runs code
- scripts/project_uvs.py 411 B runs code
- scripts/unwrap_uvs.py 396 B runs code
- tools.yaml 13 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.
- yesterday Changed · +26 lines · +7 tokens per session ad794b8bf70e
- 12d ago First seen · 49 lines · 50 tokens per session scan A c9dd954309b5
blender-uv-ops is a skill published in the GitHub repository dcc-mcp/dcc-mcp-blender (31 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 811 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
blender-reference-modeling
Build, compare, review, or repair a Blender model against an actual supplied image, photograph, concept, or visual reference using adaptive decomposition, measurable proportions, evidence scoring, and bounded repair. Use only when the request explicitly concerns model creation or quality against visual form criteria…
blender-bridge
Operate Blender Agent Bridge through its stable five-tool MCP gateway for scene inspection, modeling, materials, rigging, animation, simulation, rendering, external assets, trusted scripts, and preview decisions. Use whenever an agent must work in a live Blender scene through Blender Bridge, especially when only…
blender-mcp
Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
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…
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…
imagemagick-tools
Infrastructure skill — image processing and manipulation via ImageMagick: resize, composite, convert formats, add watermarks. Use when batch-processing textures, thumbnails, or rendered images at the file level. Not for in-DCC texture or material editing — use a domain skill bound to the specific DCC for that.