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 blender-modelinggit 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/blender-modeling)<a href="https://agentmods.dev/skills/cheshirejcat/blender/blender-modeling"><img src="https://agentmods.dev/badge/skills/cheshirejcat/blender/blender-modeling/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/cheshirejcat/blender/blender-modeling"><img src="https://agentmods.dev/badge/skills/cheshirejcat/blender/blender-modeling.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 | $0.00173 | $0.03697 |
| Opus 5 | $0.00086 | $0.01849 |
| Sonnet 5 | $0.00035 | $0.00739 |
| Haiku 4.5 | $0.00017 | $0.00370 |
Grade A, and why
blender-modeling 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.
This is a copy
95% identical to blender-modeling — 6 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Modeling
Create geometry in Blender via natural language. Emit small Python chunks through blender_python; the patterns below cover the common 80%.
Decision tree
What kind of geometry?
├── Hard-surface (vehicles, weapons, architecture, props)
│ → Cube primitive + Bevel + SubSurf modifier stack
│ → See "Hard-surface stack" recipe
│
├── Organic (characters, creatures, plants — block-out only)
│ → Ico Sphere + sculpting (or Voxel Remesh for shape)
│ → For sculpting strokes, redirect: it's gestural, not text-driven
│
├── Architectural / repeating (fences, columns, tile)
│ → Plane/Cube + Array modifier (+ Curve modifier for paths)
│ → See "Array along curve" recipe
│
├── Cylindrical (pipes, columns, bottles)
│ → Cylinder primitive, or Curve + bevel_object
│ → See "Sweep along path" — covered in wireframe-to-3d if needed
│
├── Holes / cuts in existing geometry
│ → Boolean modifier (DIFFERENCE)
│ → See "Boolean cut" recipe
│
└── Quick block-out from primitives only
→ Multiple primitive_*_add calls
→ See "Block-out scene" recipe
Code-execution rules (recap)
- Each
blender_pythoncall gets a fresh Python namespace. Re-import everything; identify objects bybpy.data.objects['name']. - Always name objects with
GEO-prefix. Never leaveCube.027. - Print structured output back so you can parse results.
- Chunk long sequences into multiple calls.
Recipes
Critical: axis orientation for elongated objects
For any elongated/asymmetric subject (sword blade, knife, bottle, plank, bone, screwdriver tip, etc.), three axes have different meaning:
- Long axis — the length of the object (78cm for a sword blade)
- Broad axis — the wider face axis, what's visible from the "useful" viewing angle (4.5cm for a blade — the flat side you'd lay on a table)
- Thin axis — the narrower cross-section axis (0.8cm for a blade — the cutting edge)
Always orient elongated objects so the broad axis faces the camera in hero shots. A sword viewed edge-on (camera looking down the thin axis) renders as a thin pole and looks nothing like a sword. The recipes below use this convention:
What ships with it
1 file 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.
- 10d ago First seen · 365 lines · 173 tokens per session scan A 394af3a846eb
blender-modeling is a skill published in the GitHub repository CheshireJCat/blender (26 stars, last pushed 21d ago), licensed MIT. It adds 173 tokens to every session and 3,697 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to blender-modeling, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
yao-image
Image expert. ALWAYS invoke this skill when you need to read, analyze, describe, or generate images. Use for screenshots, photos, charts, diagrams, AI-generated images, or any visual content.
yao-audio
Audio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.
agent-first-screenshots
Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newsletters, landing pages, social, decks, PR). Dual-channel verification (DOM + pixels + vision) in a capture loop. Use for any "take/redo screenshots of the app" task.
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…
voiceover
write the voice-over, demo script first, voiceover instead of PRD, voiceover-first development, align on the demo, script the demo, ship a feature demo-first. The whole demo-driven journey — approve the narration BEFORE any code, then build on a fresh worktree until the demo holds and open the PR with the proof on it.…