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 DanceNitra/agora --skill agora-dungeon-game-devgit 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/agora-dungeon-game-dev)<a href="https://agentmods.dev/skills/dancenitra/agora/agora-dungeon-game-dev"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/agora-dungeon-game-dev/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/agora-dungeon-game-dev"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/agora-dungeon-game-dev.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 | $0.00049 | $0.02479 |
| Opus 5 | $0.00024 | $0.01239 |
| Sonnet 5 | $0.00010 | $0.00496 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
agora-dungeon-game-dev 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎮 Agora Dungeon — Game Development Knowledge
User Preferences
- Language: English for code/docs, even when user communicates in Slovak. The user expects all code, comments, file contents, and documentation in English.
- Research workflow: When the user provides research answers from NotebookLM, save them immediately as reference files in the skill's
references/directory. One file per topic. Keep updating SKILL.md to point to new references.
Overview
Build a visually stunning 2D browser dungeon game where AI agents (like Hermes/Claude Code) operate independently, cooperate, and build real businesses. An orchestrator (human) assigns tasks. Built with TypeScript + Phaser 3 + React + Node.js + LLM API.
🧠 Knowledge from Research (8 Series — NotebookLM)
All 8 series were researched via NotebookLM using 3 books + 4 papers. Answers were saved as TypeScript reference files in references/.
Series 1: Memory Stream + Reflection (Generative Agents)
Full architecture and TypeScript implementation of the Generative Agents memory system.
Key parameters:
- Decay rate λ = 0.995 per game hour
- Importance: LLM-scored 1-10
- Retrieval = recency + importance + relevance (all α=1.0)
- Reflection trigger: sum(importance) > 150
- Reflection tree: leaf=observations, non-leaf=increasingly abstract
Reference files:
references/memory-stream-impl.md— full architecture docreferences/generative-agent-ts-implementation.ts— complete working TypeScript class
Series 2: Behavior Trees
Full BT runtime with 6 node types + Phaser 3 visual editor.
Nodes: Action, Condition, Sequence, Selector, Parallel, Inverter, Repeat Visual debug: Color-coded state display in Phaser, JSON serialization
Reference files:
references/behavior-tree-runtime.ts— core BT runtimereferences/bt-editor-phaser.ts— Phaser 3 visual editor + BTFactory
Series 3: Pathfinding + Steering
A* pathfinding + steering behaviors integrated into Phaser 3.
What ships with it
24 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/a-star-pathfinding.ts 12 KB runs code
- references/agora-integration.md 1.8 KB
- references/behavior-tree-runtime.ts 8.2 KB runs code
- references/behavior-trees-pattern.md 1.6 KB
- references/bt-editor-phaser.ts 8.1 KB runs code
- references/coalition-shapley.ts 5.1 KB runs code
- references/combat-scene.ts 7.2 KB runs code
- references/contract-net-protocol.ts 7.0 KB runs code
- references/dialogue-manager.ts 4.6 KB runs code
- references/fuzzy-logic.ts 6.4 KB runs code
- references/generative-agent-ts-implementation.ts 7.9 KB runs code
- references/generative-agents-full-architecture.md 7.9 KB
- references/generative-agents-pattern.md 2.1 KB
- references/hierarchical-fsm.ts 8.1 KB runs code
- references/inventory-scene.ts 4.3 KB runs code
- references/llm-router.ts 13 KB runs code
- references/memory-stream-impl.md 7.0 KB
- references/minimap-scene.ts 3.4 KB runs code
- references/react-pattern.md 1.6 KB
- references/steering-behaviors-phaser.ts 10 KB runs code
- references/tilemap-scene.ts 3.3 KB runs code
- references/trust-engine.ts 1.9 KB runs code
- references/utility-ai.ts 5.4 KB runs code
- references/voyager-pattern.md 2.2 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.
- 10d ago First seen · 187 lines · 49 tokens per session scan A e57f9b5d5cf4
agora-dungeon-game-dev is a skill published in the GitHub repository DanceNitra/agora (3 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 2,479 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 2026-08-31.
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-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-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-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.