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/garyfigno/dr.wangagent/worldclaw-openworldnpx skills add GaryFigno/Dr.WangAgent --skill worldclaw-openworldgit clone --depth 1 https://github.com/GaryFigno/Dr.WangAgentWrote 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/garyfigno/dr.wangagent/worldclaw-openworld)<a href="https://agentmods.dev/skills/garyfigno/dr.wangagent/worldclaw-openworld"><img src="https://agentmods.dev/badge/skills/garyfigno/dr.wangagent/worldclaw-openworld.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 | $0.00287 | $0.02533 |
| Opus 5 | $0.00143 | $0.01267 |
| Sonnet 5 | $0.00057 | $0.00507 |
| Haiku 4.5 | $0.00029 | $0.00253 |
Grade A, and why
worldclaw-openworld 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 5d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WorldClaw — Agentic 3D Open-World Generation Blueprint
Overview
WorldClaw (Tencent Hunyuan, arXiv 2608.05248) is a fully agentic, coarse-to-fine framework that turns one open-ended text prompt into a large-scale, freely explorable, editable 3D open world: a single globally coherent terrain plus instance-level 3D assets that can be reused and edited downstream.
The whole system is an LLM agent loop (the paper uses Claude Opus 4.8 as the agent brain) that drives a fixed cast of specialized sub-agents, each calling foundation models (GPT-Image-2, SAM3, SAM3D, Hunyuan3D) and a 3D DCC tool (Blender via MCP). The final world is:
S = Compose(T, O) # official formula — "explicit, explorable, editable"
# T = global terrain foundation (one continuous height-field + materials + scattered mid-scale props)
# O = set of editable instance meshes, placed on T with recovered camera-accurate poses
This skill is the operational blueprint: which stage does what, in what order, and — for our stack — which existing tool to call at each step.
Status — read this first (do not hallucinate a CLI)
- No runnable pipeline code. The GitHub repo has two branches, neither ships a
CLI/API (verified 2026-08-12):
main= a stub (title,pipeline.jpg, news, citation, links);web= the project-page source (React/Vite) — rich reference content (canonical text, 11 reference prompts, G-buffer QA pattern, asset-sourcing matrix) but not executable generation code. There is noworldclawbinary, pip package, or API. - Therefore: never invent a
worldclawcommand. This skill is implemented by you orchestrating the components below. Treat it as an architecture to assemble, not a product to invoke. - Our value-add: the components WorldClaw depends on are already in our skill library (Hunyuan3D for assets, OpenAI image API for layouts/compositions, Blender MCP for assembly). We can build a WorldClaw-style pipeline today.
What ships with it
8 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.
- references/agent-architecture.md 5.1 KB
- references/blender-mcp-setup.md 4.2 KB
- references/hd2d-adapter-design.md 8.4 KB
- references/method-details.md 7.6 KB
- references/pipeline-blueprint.md 8.8 KB
- references/reproduction-plan.md 15 KB
- references/sam3d-integration.md 5.4 KB
- references/scenes-prompts-and-qa.md 7.1 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.
- 5d ago First seen · 153 lines · 287 tokens per session scan A 55c85a216d5a
worldclaw-openworld is a skill published in the GitHub repository GaryFigno/Dr.WangAgent (2 stars, last pushed 17d ago), licensed MIT. It adds 287 tokens to every session and 2,533 once invoked, about $0.0014 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 2026-08-31.
Other skills, from other repositories
sprite-atlas-builder
Sprite atlas pipeline. Use for sprites, tilesets, textures, asset sheets, extraction, curation, and QA.
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…