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 agentmods add skills/horizonrobotics/embodiedgen/asset-processnpx skills add HorizonRobotics/EmbodiedGen --skill asset-processgit 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/asset-process)<a href="https://agentmods.dev/skills/horizonrobotics/embodiedgen/asset-process"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/asset-process.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 | $0.00062 | $0.00827 |
| Opus 5 | $0.00031 | $0.00413 |
| Sonnet 5 | $0.00012 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
asset-process 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 6d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Processing
Overview
Use this skill to scale or rotate an asset and all of its supported geometry files consistently. Rotation is provided as XYZ Euler angles in degrees and is applied around the asset's local origin.
The input URDF may use either supported asset layout:
<asset_dir>/result/<asset_name>.urdf
<asset_dir>/<asset_name>.urdf
The mesh directory must be beside the URDF as mesh/.
Normal mode copies the complete asset directly to <output_dir>. Pass the
full target asset directory, including the desired asset directory name.
Inplace mode modifies the source asset.
After processing, the tool calculates the transformed mesh's Y-axis extent and
writes that value to min_height, max_height, and real_height in the URDF.
It uses the main OBJ first, then the GLB, then the collision OBJ.
CLI Examples
Scale Only
python -m embodied_gen.skills.asset-process.asset_process \
--urdf-path outputs/assets/red_box/result/red_box.urdf \
--scale-factor 0.8 \
--output-dir outputs/processed
Rotate Only
python -m embodied_gen.skills.asset-process.asset_process \
--urdf-path outputs/assets/red_box/result/red_box.urdf \
--rot-xyz 90 0 45 \
--output-dir outputs/processed
Scale and Rotate
python -m embodied_gen.skills.asset-process.asset_process \
--urdf-path outputs/test_wuwen/facial_cleanser_001/facial_cleanser_001.urdf \
--scale-factor 1.0 \
--rot-xyz 0 90 0 \
--keep-urdf-raw-rot \
--output-dir outputs/test_wuwen/facial_cleanser_001_processed
--keep-urdf-raw-rot is optional. When enabled, the inverse baked rotation is
composed into visual and collision origin rpy values so their effective
rotation remains unchanged. It is disabled by default.
Process Inplace
python -m embodied_gen.skills.asset-process.asset_process \
--urdf-path outputs/assets/red_box/result/red_box.urdf \
--scale-factor 0.8 \
--rot-xyz 0 0 90 \
--inplace
Inplace mode modifies the original asset files.
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.
- 6d ago First seen · 102 lines · 62 tokens per session scan A 08497463ab4a
asset-process is a skill published in the GitHub repository HorizonRobotics/EmbodiedGen (654 stars, last pushed 12d ago), licensed Apache-2.0. It adds 62 tokens to every session and 827 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.