sim-runner

sim-runner is a skill for Claude Code, Codex from HorizonRobotics/EmbodiedGen. It costs 53 tokens per session (642 once invoked), scanned A, original, Apache-2.0.

A skill for rendering EmbodiedGen layouts in SAPIEN, a physics simulation platform, with sim-cli. It loads an existing layout.json and produces an interactive scene video.

In plain words
What is it for?
Use it to render layouts, adjust camera or simulation steps, and show robot grasping in the resulting video.
Why use it?
It connects generated layouts to simulation without requiring you to assemble the rendering command yourself. It can also include a robot grasp trajectory and camera or rendering settings.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/horizonrobotics/embodiedgen/sim-runner
Any agent
npx skills add HorizonRobotics/EmbodiedGen --skill sim-runner
Clone the repo
git clone --depth 1 https://github.com/HorizonRobotics/EmbodiedGen

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sim-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/sim-runner.svg)](https://agentmods.dev/skills/horizonrobotics/embodiedgen/sim-runner)
Your own site
<a href="https://agentmods.dev/skills/horizonrobotics/embodiedgen/sim-runner"><img src="https://agentmods.dev/badge/skills/horizonrobotics/embodiedgen/sim-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00642
Opus 5 $0.00026 $0.00321
Sonnet 5 $0.00011 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 4d ago against content hash 4630219d662c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sim-runner 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 4d 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.

embodied_gen/skills/sim-runner/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sim Runner

Unified entry for EmbodiedGen simulation rendering via sim-cli.

When To Use

Use this skill when users want to:

  • Load a generated layout.json into simulation.
  • Render interactive scene videos (foreground + 3DGS background composition).
  • Adjust camera, rendering, or simulation-step parameters.
  • Include robot grasp trajectory rendering with --insert_robot.

Routing Rule (Core)

Use sim-cli when the input is an existing layout result (especially layout.json) and the target output is simulation visualization (e.g., Iscene.mp4), not generation of new assets/backgrounds/layouts.

Pre-checks

  1. Run commands from the repository root.
  2. Confirm the active environment is embodiedgen.
  3. Confirm input --layout_path exists and points to a valid layout output.
  4. Ensure referenced background and asset files in the layout directory are present.
  5. If CLI commands are unavailable, run pip install -e . to register entrypoints.

Standard Command Template

sim-cli \
  --layout_path "outputs/layouts_gen/task_0000/layout.json" \
  --output_dir "outputs/layouts_gen/task_0000/sapien_render" \
  --insert_robot

Common Parameters

  • --layout_path: input layout file path.
  • --output_dir: output directory for rendered video.
  • --insert_robot: render robot grasp actions for manipulated objects.
  • --sim_freq --control_freq --sim_step: simulation/control timing settings.
  • --render_interval: render every N simulation steps.
  • --num_cameras --camera_radius --camera_height --fovy_deg: camera configuration.
  • --image_hw: output frame size.
  • --render_keys: render channels (requires Foreground for final compositing).
  • --ray_tracing: enable/disable ray tracing backend.
  • --device: rendering device (e.g., cuda).

Output Conventions

Primary output:

  • <output_dir>/Iscene.mp4

Typical input dependencies resolved from layout directory:

  • layout.json
  • background gs_model.ply
  • per-object assets referenced by layout

Read the full file on GitHub · 72 lines

Changes

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.

  1. 4d ago First seen · 72 lines · 53 tokens per session scan A 4630219d662c

Subscribe to this mod's changes

sim-runner is a skill published in the GitHub repository HorizonRobotics/EmbodiedGen (648 stars, last pushed 10d ago), licensed Apache-2.0. It adds 53 tokens to every session and 642 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.