Borrowing it
Nothing to install: this file belongs to DanceNitra/agora. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DanceNitra/agora/main/.claude/skills/dungeon-os-threejs/SKILL.mdgit clone --depth 1 https://github.com/DanceNitra/agoraWrote 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/dancenitra/agora/dungeon-os-threejs)<a href="https://agentmods.dev/skills/dancenitra/agora/dungeon-os-threejs"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/dungeon-os-threejs/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/dancenitra/agora/dungeon-os-threejs"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/dungeon-os-threejs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00110 | $0.03269 |
| Opus 5 | $0.00055 | $0.01635 |
| Sonnet 5 | $0.00022 | $0.00654 |
| Haiku 4.5 | $0.00011 | $0.00327 |
Grade A, and why
dungeon-os-threejs 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 12d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dungeon OS — Three.js World Builder
The 3D dungeon is a 2.5-D isometric night scene where six LLM-driven agents move around and build an "Agentic OS." The renderer is a view of game state — it reads state over a WebSocket and never owns game logic.
Before writing render code, read the two source-of-truth files (don't trust memory):
agora-game-server/static/index.html— the entire renderer (single-file vanilla ESM Three.js, ~1500 lines).agora-game-server/game_state.py—GameEngine/DungeonState(the tilemap + entities the scene renders). Run it:cd agora-game-server && python mcp_server.py→ openhttp://localhost:5174. The dungeon process is launched/restarted by the loop's standard procedure; after editingindex.htmlyou only need a browser hard-refresh (it's served raw, no build step).
GROUND TRUTH — the actual stack (build to match this, not a target)
| Concern | Reality |
|---|---|
| Three.js | r0.170.0, vendored at agora-game-server/node_modules/three. ESM via <script type="importmap">: "three" → /node_modules/three/build/three.module.js, "three/addons/" → /node_modules/three/examples/jsm/. |
| Renderer | WebGLRenderer({ antialias:true }) — synchronous, no await init(). setPixelRatio(min(dpr,2)), shadowMap.enabled, PCFSoftShadowMap, ACESFilmicToneMapping, toneMappingExposure ≈ 1.45. (A WebGPU build three.webgpu.js is vendored but UNUSED — see Upgrade Path before touching it.) |
| Camera | OrthographicCamera iso, d ≈ 15, position (d,d,d) looking at (0,0,0), OrbitControls (rotation NOT locked yet). |
| Atmosphere | scene.background = 0x0a0e18 (deep night); scene.fog = new THREE.Fog(0x0a0e18, 45, 95) (linear, matches bg). |
| Lights | AmbientLight(0x37466a, .5) + cool moonlight DirectionalLight(0x9fb2da, 1.0) with a tight shadow frustum (±16) for crisp shadows + HemisphereLight(0x5a6e98, 0x2a2420, .5) + ~9 warm torch PointLights from state (radius, decay 1.8) + cheap emissive flame meshes flickered each frame. Point lights are sparse ON PURPOSE. |
| Floors/walls/props | The Quaternius "Ultimate Modular Ruins Pack" (Floor_Standard, Floor_Diamond, Wall*, Statue_*, Flag_Wall, columns…). Loaded once into a ruinsCache, then one clone per tile (floors are real models, not boxes; one tinted template per zone colour). |
| Agents | 6 (King Aldric, Sgt Voss, Dame Elara, High Priest Orin, Shadow Kael, Sage Mira). Quaternius glTF, cloned with SkeletonUtils.clone, one AnimationMixer each, tweened movement, CanvasTexture Sprite labels (name / HP bar / thought bubble). |
| State→view | Client opens WS :5175, gets a snapshot, applies incremental events (entity_moved/state/health/thought/face, tasks_update, effect_added, os_build, trust/HUD). Reads, never writes. HTTP is :5174. |
| Post-processing | NONE yet. EffectComposer, UnrealBloomPass, SSAOPass, GTAOPass, SMAAPass, OutputPass are all present in node_modules/three/examples/jsm/postprocessing/ and unused. This is the single biggest visual win available. |
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.
- 12d ago First seen · 134 lines · 110 tokens per session scan A 44969717e0a4
dungeon-os-threejs is a skill published in the GitHub repository DanceNitra/agora (3 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 3,269 once invoked, about $0.0006 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
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
arc-skill
Solve an interactive hidden-rule ARC-AGI-3 game from its game ID. Contains the complete playing doctrine (predict before every action, graded claims, one-page notes, optional executable-rules search) plus the arc harness the agent drives. Use whenever asked to solve, play, or continue an ARC-AGI-3 game.
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-fundamentals
Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.
threejs-world-generation
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…
sound-effects
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.