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 LiteReality/LiteReality-Agent --skill image-to-articulated-glbgit clone --depth 1 https://github.com/LiteReality/LiteReality-AgentWrote 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/litereality/litereality-agent/image-to-articulated-glb)<a href="https://agentmods.dev/skills/litereality/litereality-agent/image-to-articulated-glb"><img src="https://agentmods.dev/badge/skills/litereality/litereality-agent/image-to-articulated-glb/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/litereality/litereality-agent/image-to-articulated-glb"><img src="https://agentmods.dev/badge/skills/litereality/litereality-agent/image-to-articulated-glb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.04238 |
| Opus 5 | $0.00048 | $0.02119 |
| Sonnet 5 | $0.00019 | $0.00848 |
| Haiku 4.5 | $0.00010 | $0.00424 |
Grade A, and why
image-to-articulated-glb 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 2d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image → Articulated GLB (with PBR textures + render verification)
Pipeline for turning a reference image of furniture/objects into a GLB with movable parts, embedded PBR textures, and rendered visual proof.
Invocation arguments
When invoked as /image-to-articulated-glb <args>, parse them as:
- arg 1 — reference image path (required). If missing or the file doesn't exist, ask for it before doing anything else.
- arg 2 (optional) — output GLB path, or a directory (then use
<dir>/<image_basename>.glb). Default when omitted:<image_dir>/<image_basename>_glb/<image_basename>.glb.
With valid args, run the FULL pipeline end-to-end without pausing for
confirmation: analyze image → fetch textures → build → validate → render-check
→ emit a self-contained object.py + object.md → final report showing both
preview PNGs, the GLB path, and the articulation summary. Put every artifact
(textures/, previews/, the build recipe, object.py, object.md) in the output
GLB's directory so each job is self-contained.
Deliverables per object (in the GLB's directory):
<stem>.glb— the model (embedded textures + articulation extras + animations)object.py— a self-contained Blender script that rebuilds it on its own (no external imports / sys.path hacks); runs withblender -b --python object.pyobject.md— how to edit the object (constants, articulation, rebuild command)previews/,textures/, and the readable build recipe
All reusable scripts live in scripts/ next to this file. Blender binary:
/opt/homebrew/bin/blender (fall back to blender on PATH; the desktop app is
at /Applications/Blender.app). The blender-mcp addon is usually NOT connected —
go headless CLI by default; only try MCP tools if the user says Blender is open.
Workflow
1. Analyze the reference image
Read the image. Identify: overall object type and real-world dimensions (estimate, meters), which parts are movable (drawers → prismatic slide, doors/lids → revolute hinge), handle/hardware style, material (wood tone, metal, plastic), and small details (casters, grommets, vents). State the analysis to the user before building.
What ships with it
12 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.
- build_table0_desk.py 4.4 KB runs code
- scripts/.gitignore 190 B
- scripts/blender_lib.py 20 KB runs code
- scripts/completeness_check.py 5.9 KB runs code
- scripts/example_build_desk.py 4.1 KB runs code
- scripts/fetch_polyhaven.py 1.9 KB runs code
- scripts/make_selfcontained.py 5.9 KB runs code
- scripts/merge_animations.py 3.7 KB runs code
- scripts/object_model.py 12 KB runs code
- scripts/probe_glb.py 16 KB runs code
- scripts/render_glb_preview.py 5.5 KB runs code
- scripts/validate_glb.py 2.9 KB runs code
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.
- 2d ago Changed · +31 lines 0ad9ae687767
- 12d ago First seen · 240 lines · 96 tokens per session scan A 5df9aef5a192
image-to-articulated-glb is a skill published in the GitHub repository LiteReality/LiteReality-Agent (410 stars, last pushed today), licensed Apache-2.0. It adds 96 tokens to every session and 4,238 once invoked, about $0.0005 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.