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 asset-retrievalgit 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-retrieval)<a href="https://agentmods.dev/skills/horizonrobotics/embodiedgen/asset-retrieval"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/asset-retrieval/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/asset-retrieval"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/asset-retrieval.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 | $0.00066 | $0.00737 |
| Opus 5 | $0.00033 | $0.00368 |
| Sonnet 5 | $0.00013 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
asset-retrieval 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Retrieval
Look up simulation-ready assets from dataset_index.csv and return .urdf
paths. The CSV index is the single source of truth.
Workflow
Preferred — agent reads CSV directly:
- Read
dataset_index.csvinto context. - Semantically match the user's description (open-ended, fuzzy, or in any
language) against
category,secondary_category,primary_category, anddescriptioncolumns. - Return the best-matching absolute
.urdfpath; return multiple candidates when the request is broad or explicitly asks for several. - Briefly explain why the returned asset matches.
This path handles open-ended queries like "a tall chair suitable for a coffee shop" or "能放在客厅角落的落地灯" that pure keyword matching cannot resolve.
Fallback — CLI script (no network / no LLM):
When the agent is unavailable, use the helper script which performs offline keyword-based ranking:
python embodied_gen/skills/asset-retrieval/scripts/retrieve_asset.py \
"modern dining chair curved backrest"
For the CLI path, rewrite open-ended or Chinese descriptions into compact
English keywords first (e.g. 能放在客厅角落的落地灯 → floor lamp).
Index Resolution
Checked in order — first match wins:
--index-fileCLI argument$EMBODIEDGEN_DATASET_INDEXenvironment variable$EMBODIEDGEN_DATASET_ROOT/dataset_index.csv<repo-root>/outputs/EmbodiedGenData/dataset/dataset_index.csv
Dataset root follows a parallel order (--dataset-root →
$EMBODIEDGEN_DATASET_ROOT → repo default).
Required CSV Columns
uuid, primary_category, secondary_category, category, description,
generate_time, urdf_path
Query Guidelines
- Use explicit object words:
chair,bar stool,remote control. - Keep discriminating modifiers:
wooden,orange,modern,round. - Open-ended or Chinese descriptions are fine for the agent path; rewrite to English keywords only when using the CLI script.
Script Usage
# Single best match (absolute path on stdout)
python embodied_gen/skills/asset-retrieval/scripts/retrieve_asset.py \
"modern dining chair curved backrest"
# Multiple candidates with scores
python embodied_gen/skills/asset-retrieval/scripts/retrieve_asset.py \
"orange cushioned bar stool" \
--top-k 5 --format json
# Custom dataset location
python embodied_gen/skills/asset-retrieval/scripts/retrieve_asset.py \
"black remote control" \
--dataset-root /path/to/dataset \
--index-file /path/to/dataset/dataset_index.csv
# Relative paths instead of absolute
python embodied_gen/skills/asset-retrieval/scripts/retrieve_asset.py \
"wooden bar stool" --relative-paths
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 · 88 lines · 66 tokens per session scan A fa5001eda00d
asset-retrieval is a skill published in the GitHub repository HorizonRobotics/EmbodiedGen (660 stars, last pushed 16d ago), licensed Apache-2.0. It adds 66 tokens to every session and 737 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).
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…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
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.