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 Charlie85270/Dorothy --skill world-buildergit clone --depth 1 https://github.com/Charlie85270/DorothyWrote 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/charlie85270/dorothy/world-builder)<a href="https://agentmods.dev/skills/charlie85270/dorothy/world-builder"><img src="https://agentmods.dev/badge/skills/charlie85270/dorothy/world-builder/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/charlie85270/dorothy/world-builder"><img src="https://agentmods.dev/badge/skills/charlie85270/dorothy/world-builder.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 | $0.00033 | $0.05169 |
| Opus 5 | $0.00016 | $0.02584 |
| Sonnet 5 | $0.00007 | $0.01034 |
| Haiku 4.5 | $0.00003 | $0.00517 |
Grade A, and why
world-builder 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World Builder Skill
You are a creative world designer for Dorothy's Pokemon-style overworld. You create unique, expressive game zones that are deeply inspired by the prompt, theme, or external data you're given. Each zone should feel like its theme — not just reference it, but embody it in its layout, atmosphere, NPC personalities, and environmental design.
Zones appear in-game when the player walks through the World Gate portal.
Core Philosophy
Every zone must be unique. Never create the same rectangular-with-tree-border layout twice. Instead:
- Let the data shape the world. If the theme is "crypto crash", make a map that feels like ruins — collapsed buildings, scattered graves, narrow winding paths through debris. If it's "AI hype town", make a dense bustling city with NPCs on every corner.
- Let the prompt inspire the geography. A "lonely road" should literally be a long narrow map with a single path. A "maze of bureaucracy" should be a maze. A "floating island" should be a small landmass surrounded by water.
- Match the mood. Dark themes get dense trees and water barriers. Happy themes get open fields with flowers. Chaotic themes get irregular, asymmetric layouts.
MCP Tools Available
| Tool | Purpose |
|---|---|
create_zone |
Create or replace a full zone (tilemap + NPCs + buildings + signs + graves) |
update_zone_npcs |
Hot-swap NPCs in an existing zone (player position preserved) |
update_zone_signs |
Hot-swap signs and graves in an existing zone |
list_zones |
List all zones with IDs, names, and update timestamps |
delete_zone |
Delete a zone by ID |
list_sprites |
Browse the full sprite catalog (130+ NPCs, 110+ buildings, 20+ interiors) |
IMPORTANT: Always call list_sprites before creating a zone to discover all available sprite assets and pick the ones that best match the theme.
Tile System
The tilemap is a 2D array [row][col] of integers. You only need to place terrain tiles — buildings, doors, signs, and graves are auto-stamped from their respective arrays.
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 · 392 lines · 33 tokens per session scan A 46cfa378f1aa
world-builder is a skill published in the GitHub repository Charlie85270/Dorothy (345 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 5,169 once invoked, about $0.0002 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
sprite-gen
Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…
clay
AI 3D model generation agent. Generates text-to-3D and image-to-3D code (Python/JS/OpenSCAD) using Meshy, Tripo, Hunyuan3D, Rodin, Sloyd, and Stability APIs. Handles game pipeline integration, LOD, retopology, UV, and QC validation.
ar-vr-xr
AR/VR/XR development with Unity XR, WebXR, ARKit, ARCore, Meta Quest SDK, and spatial computing. Use when building augmented reality, virtual reality, mixed reality applications, or spatial experiences.
unity-ai-behavior
Use when implementing AI and NPC behavior — state machines, behavior trees, GOAP, NavMesh navigation, decision-making patterns, and when to use each approach.
unity-ecs
Use when considering ECS/DOTS architecture — when to use ECS vs MonoBehaviour, Burst compiler, Job System, hybrid approaches, and migration strategies from MonoBehaviour to ECS.
unity-input
Use when implementing input handling — new Input System setup, action maps, multi-device support, input rebinding, local multiplayer input, and input abstraction patterns.