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 HorizonRobotics/EmbodiedGen --skill spatial-computinggit clone --depth 1 https://github.com/HorizonRobotics/EmbodiedGenWrote 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/horizonrobotics/embodiedgen/spatial-computing)<a href="https://agentmods.dev/skills/horizonrobotics/embodiedgen/spatial-computing"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/spatial-computing/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/horizonrobotics/embodiedgen/spatial-computing"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/spatial-computing.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 | $0.00079 | $0.04044 |
| Opus 5.5 | $0.00032 | $0.01618 |
| Sonnet 5.5 | $0.00016 | $0.00809 |
| Haiku 4.5 | $0.00008 | $0.00404 |
Grade A, and why
spatial-computing 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 — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Floorplan & Object Placement/Deletion
Overview
Parse indoor scenes from URDF, generate 2D floorplans, or place/remove 3D objects in scenes and write back to URDF/USD. After successful insertion/deletion, the corresponding file is automatically updated based on whether urdf_path/usd_path is provided.
When to use: Use this skill when you need to generate floorplans from URDF, place/delete objects on specified rooms/furniture surfaces, or batch update URDF/USD files.
⚠️ USD updates require
room-cli: To update USD files, you must useroom-cliinstead ofpython -m, and specify the USD file via--usd_path.room-cliruns on Blender Python which includes thebpymodule for OBJ→USD conversion; usingpython -mwith--usd_pathwill fail withModuleNotFoundError: No module named 'bpy'.# ✅ Correct: use room-cli to update both URDF and USD room-cli -m embodied_gen.skills.spatial-computing.cli.main \ --urdf_path .../scene.urdf --usd_path .../scene.usdc ...
Smart File Naming Strategy:
- Default behavior: First operation creates
scene_updated.urdf, subsequent operations automatically overwrite it - No file bloat: Prevents
*_updated_updated.urdffiles from accumulating - Safe: Original
scene.urdfis never modified unless explicitly requested - Works for both insert and delete: Seamless continuous scene editing
Best Practices & Constraints
1. Workflow for Continuous Scene Editing
Recommended workflow for multiple insert/delete operations:
# Step 1: View current scene
python -m embodied_gen.skills.spatial-computing.cli.main \
--urdf_path .../scene.urdf --list_instances
# Step 2: First insert → creates scene_updated.urdf
python -m embodied_gen.skills.spatial-computing.cli.main \
--urdf_path .../scene.urdf \
--asset_path .../apple.obj --instance_key apple_1
# Step 3: Second insert → overwrites scene_updated.urdf
python -m embodied_gen.skills.spatial-computing.cli.main \
--urdf_path .../scene_updated.urdf \
--asset_path .../lamp.obj --instance_key lamp_1
# Step 4: Delete operation → overwrites scene_updated.urdf
python -m embodied_gen.skills.spatial-computing.cli.main \
--urdf_path .../scene_updated.urdf \
--delete_instance apple_1
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.
- __init__.py 925 B runs code
- api/__init__.py 1.0 KB runs code
- api/floorplan_api.py 31 KB runs code
- cli/__init__.py 170 B runs code
- cli/main.py 8.6 KB runs code
- core/__init__.py 652 B runs code
- core/collector.py 40 KB runs code
- core/geometry.py 6.9 KB runs code
- core/trajectory.py 33 KB runs code
- core/visualizer.py 11 KB runs code
- README.md 3.4 KB
- REFERENCE.md 10 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.
- 1mo ago First seen · 406 lines · 79 tokens per session scan A cbb16dc49aa8
spatial-computing is a skill published in the GitHub repository HorizonRobotics/EmbodiedGen (704 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 4,044 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
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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.