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 CheshireJCat/blender --skill source-part-segmentationgit clone --depth 1 https://github.com/CheshireJCat/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/cheshirejcat/blender/source-part-segmentation)<a href="https://agentmods.dev/skills/cheshirejcat/blender/source-part-segmentation"><img src="https://agentmods.dev/badge/skills/cheshirejcat/blender/source-part-segmentation.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 | $0.00058 | $0.00734 |
| Opus 5 | $0.00029 | $0.00367 |
| Sonnet 5 | $0.00012 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
source-part-segmentation 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 7d 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.
This is a copy
100% identical to source-part-segmentation — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Part Segmentation
Use this before contour-to-mesh when a source image contains overlapping or touching designed parts.
The output is not “nice masks”; it is a source-of-truth part inventory that downstream geometry must obey.
Inputs
- source image, wireframe, decal, or texture atlas;
- optional manual seed manifest with named parts, polygons, seed points, rough rectangles, or HSV/color ranges;
- source manifest with structural/decorative/context classification and expected part count.
Workflow
- Choose the cleanest modality: alpha, edge, dark-line, bright-on-dark, color-band, or atlas region.
- Extract contours and hierarchy to identify candidate objects, holes, nested details, and strokes.
- If components touch, run distance-transform marker watershed first.
- If watershed over/under-splits, switch to seeded segmentation:
- create named part seeds (
bbox,polygon, orseed_point+ optional flood/HSV tolerance); - save one mask per named structural part;
- mark ambiguous overlaps explicitly instead of merging them.
- create named part seeds (
- Classify masks as
structural,decorative,face_feature,aura_context, orvalidation_only. - Pass structural masks to
contour-to-mesh; pass feature masks/landmarks tolandmark-fit-repair; pass atlas regions toatlas-uv-fitting.
Hard rules
- Do not infer repeated parts from symmetry; segment what the source shows.
- Do not merge overlapping components if the manifest expects separate structural meshes.
- Do not proceed to final modeling when part count differs between source images; write a conflict report or canonical policy.
- If automatic segmentation is ambiguous, write an ambiguity report and require or create manual seed rectangles/points.
- Keep stroke/line masks separate from filled-part masks; wireframe strokes are guides unless explicitly used as the contour boundary.
Seed manifest schema
{
"schema": "source_part_seed_manifest.v1",
"image": "path/to/source.png",
"parts": [
{"name":"leaf_top", "class":"structural", "bbox":[x,y,w,h], "mode":"non_background"},
{"name":"face_shell", "class":"structural", "polygon":[[x,y],[x,y],...], "mode":"polygon"}
]
}
What ships with it
2 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.
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.
- 7d ago First seen · 64 lines · 58 tokens per session scan A 190f635882ed
source-part-segmentation is a skill published in the GitHub repository CheshireJCat/blender (24 stars, last pushed 18d ago), licensed MIT. It adds 58 tokens to every session and 734 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to source-part-segmentation, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ipollowork-template-generation
Create or update reusable iPolloWork templates through conversation for Design, Slides/native editable PPT, and HyperFrames Video. Use when planning, generating, repairing, validating, or saving a template package, manifest, reusable variables, cover, slide/PPT markers, video composition, or design-system token…
autonomous-modeling
Use this skill to autonomously design and model complex 3D objects in Blender. Perfect for generating chassis, robots, and environment props from natural language.
xiaohongshu-cover
An AI cover-planning tool for Xiaohongshu, a Chinese social platform for lifestyle and product content. It studies popular covers in a topic area and produces three cover concepts with examples and image-generation prompts.
wireframe-to-3d
Convert 2D orthographic wireframe PNG drawings to 3D Blender models exported as glTF/GLB. Use this skill whenever the user provides wireframe images (technical drawings, line drawings, orthographic views, side/front/back panels) and wants to generate a 3D model, mesh, or .glb file. Triggers on phrases like "convert…
mascot-logo-reconstruction
Orchestrate a fail-gated, source-locked Blender reconstruction of mascots, logos, brand avatars, and stylized flat characters from wireframes, texture packs, and orthographic views. Use when the user requires a 1:1 brand/model match rather than a plausible stylized interpretation.
source-part-segmentation
Segment overlapping visual parts from source images, wireframes, texture atlases, and decals before mesh reconstruction. Use when a mascot/logo/template contains touching or overlapping components and exact structural part masks are needed before contour-to-mesh, UV fitting, or landmark repair.