build-games-and-playful-experiences

build-games-and-playful-experiences is a skill for Claude Code, Codex from EverMind-AI/Raven. It costs 112 tokens per session (3,306 once invoked), scanned A, original, Apache-2.0.

A guide for building, changing, diagnosing, and checking two-dimensional games and playful experiences. It covers games, interactive toys, story exploration, rhythm experiences, generative experiences, and local multiplayer.

In plain words
What is it for?
Use it to define the player's actions and goals, build the rules and feedback, choose suitable tools, and check controls, content, sound, accessibility, platform limits, and local multiplayer behavior.
Why use it?
It helps separate a game that merely runs from one that is understandable, fair, enjoyable, recoverable, and worth replaying. It also prevents testing technical details from being mistaken for proof that the experience is fun.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: $skill-name invocation.

Good fit Use it to define the player's actions and goals, build the rules and feedback, choose suitable tools, and check controls, content, sound, accessibility, platform limits, and local multiplayer behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evermind-ai/raven/build-games-and-playful-experiences
About the project

Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.

EverMind-AI/Raven · 3,825 stars · on GitHub · raven.evermind.ai

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.

Any agent
npx skills add EverMind-AI/Raven --skill build-games-and-playful-experiences
Clone the repo
git clone --depth 1 https://github.com/EverMind-AI/Raven

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 build-games-and-playful-experiences

README.md
[![agentmods](https://agentmods.dev/badge/skills/evermind-ai/raven/build-games-and-playful-experiences/github.svg)](https://agentmods.dev/skills/evermind-ai/raven/build-games-and-playful-experiences)
Your own site
<a href="https://agentmods.dev/skills/evermind-ai/raven/build-games-and-playful-experiences"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-games-and-playful-experiences/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.

agentmods 80×15 button for build-games-and-playful-experiences

Your own site · 80×15
<a href="https://agentmods.dev/skills/evermind-ai/raven/build-games-and-playful-experiences"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-games-and-playful-experiences.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00112 $0.03306
Opus 5 $0.00056 $0.01653
Sonnet 5 $0.00022 $0.00661
Haiku 4.5 $0.00011 $0.00331

Measured today against content hash 9bd9f7cb54ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

build-games-and-playful-experiences 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 today.

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.

plugins-dist/design-engine/raven_design/skills/build-games-and-playful-experiences/SKILL.md · 134 lines

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.

构建游戏与趣味体验

本 Skill 拥有二维游戏的玩家合同、领域 gate、专业 claim ceiling 与失败返回;通用 authority、 tool-use、渲染、review、promotion 与交付规则沿用共享视觉底座。

成功不是页面会动或测试全绿,而是玩家通过公开输入改变规则状态、看懂因果、获得下一次有意义行动,并能按合同停止、恢复或返回。工程证据只能证明其实际覆盖的技术事实。

1. 路由与合同

先声明任务模式。Create 建立新的玩家合同、原生母版与交付;Edit 只改变授权范围并重跑受影响 gate;Diagnose/Audit 只复现、读取和归因,不把诊断默认为修改授权。

选择一个主子型;混合形态要说明主从关系:

  • 二维规则/动作/益智:价值来自决策、执行、发现约束或掌握。
  • 互动玩具:价值来自持续介入、材料反馈、组合和表达,不强造胜负。
  • 叙事探索:价值来自移动、观察、选择及世界回应,不是被动翻页。
  • 节奏体验:价值来自输入与统一时间基准的关系。
  • 生成体验:价值来自受约束变化、种子、定格或可比较结果,不是随机噪声。
  • 本地多人:价值来自共享设备前的轮流、同时操作或协商;线上权威状态不在本版能力范围。

主要价值若是理解模型,转交交互解释器;若是编辑、管理或导出工作结果,转交产品工具界面;若是观看场景,转交插画与视觉场景。积分、徽章、动画和开始按钮不构成游戏。

本版只覆盖二维。三维只可路由到 unity-3d-runtime-futureunreal-engine-3d-runtime-futuregodot-3d-runtime-futureblender-3d-content-future:这些 profile 尚未验证,必须停止三维能力声明并返回工具选择或人类交接,不能用二维证据外推。

动手前同时锁定两份合同:

  • 玩家合同:受众与真实设备、主要动词、核心循环、最低完成/主动停止、失败与恢复、返回价值、输入方式、内容规模、音频职责、可访问性风险、平台预算、目标 claims 与明确非目标。
  • 交付合同:最终消费者、真实消费设备/渠道、目标 renderer 或运行时、权威母版、交付格式、来源与许可、重建入口、最终像素或最终验收方法,以及各自不支持的 claims。

保持介质中立:由最终消费者决定浏览器、原生运行时、安装包、街机/展陈设备或其他二维媒介,不因可网页预览就预设 HTML、Canvas、固定比例或应用外壳。非网页媒介必须在目标 renderer、设备或物理环境中验收;浏览器截图、DOM、Gallery 和网页 wrapper 不能冒充其最终消费者证据。

只有最终消费者明确是 Web 时才加载 $build-polished-visual-frontends,由它补充 Web 技术栈、响应式和最终网页视觉执行;非 Web 主交付不加载该 Skill。本 Skill 始终拥有玩家合同、规则和领域 gate。

验证计划按 claim 和风险生成,不设固定人数、轮数、视口或阈值。音频启用/解码仅在合同包含声音时检查;存档/迁移仅在承诺持久化时检查;离线边界仅在承诺离线运行时检查。未触发项写明可验证的范围理由,不把未知、未实现或工具不可用写成 N/A。

2. 工具与 authority 接口

先从 工具能力档案 将“子型 → 所需能力 → 具体工具 profile”写清。有 Registry canonical ID 时按其查询共享 Tool Registry;仅有 candidate ID 时按原 ID 查询并如实保留缺项。每次任务读取当前 Registry 与环境 probe,不在 Skill 缓存“已登记”或“可用”状态;Registry 缺项、未安装或需商业 GUI 时,分别记录 candidate_unavailable/治理记录中的 unavailablehuman_handoff

选定工具后,让其原生场景、显示树、资源、时间、输入、关卡、图层、轨道或导出模型成为实现结构;不要只借一个控件,其余重新手写。每个 concern 只能有一个权威 owner,至少区分规则/状态、内容/关卡、视觉资产、音频、输入映射和自动测试;截图、构建包与 Gallery 均为派生物。

工具只有具备版本与许可、真实调用、可编辑母版、重建/导出和当前 consumer/像素证据时才是 used。工具不可用只触发替代或交接,不证明它缺能力。

手写运行时、编辑器、渲染器、输入层或资源管线前,必须实际执行成熟候选的 capability probe;仅当结果为 fail 才记录 gap、最小自定义边界及数据/交互/视觉/导出一致性证据。偏好手写或环境未安装都不是 gap。

Read the full file on GitHub · 134 lines

Files

What ships with it

2 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.

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. today First seen · 134 lines · 112 tokens per session scan A 9bd9f7cb54ab

Subscribe to this mod's changes

build-games-and-playful-experiences is a skill published in the GitHub repository EverMind-AI/Raven (3,825 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 3,306 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 2026-09-12.