Borrowing it
Nothing to install: this file belongs to DY-2026/GameDesignOS. 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/DY-2026/GameDesignOS/main/AGENTS.mdgit clone --depth 1 https://github.com/DY-2026/GameDesignOSWrote 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/instructions/dy-2026/gamedesignos/agents-md)<a href="https://agentmods.dev/instructions/dy-2026/gamedesignos/agents-md"><img src="https://agentmods.dev/badge/instructions/dy-2026/gamedesignos/agents-md.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 | $0.00972 | $0.00972 |
| Opus 5 | $0.00486 | $0.00486 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
GameDesignOS AGENTS.md 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GameDesignOS Agent 入口
这份文件给 Codex、Claude Code、OpenCode 等支持 AGENTS.md 的 agent 使用。目标是让用户拉取项目后,不需要先读完整 README,也不需要知道每个 skill 名字。
默认接法
当用户在这个仓库里随便发一句游戏设计、立项、体验分析、资料整理、翻译、工作流升级或策划案需求时,先走自然语言入口:
python -m gamedesignos ask "<用户原话>"
如果用户没有写 ask,也可以直接执行:
python -m gamedesignos "<用户原话>"
这个入口会做三件事:
- 推荐应该使用的 skill,并给出可审计的
Use $skill-name ...提示词; ask默认只做路由和状态审计;只有用户显式提供--destination/--workspace,或明确调用start,才创建或恢复 Project-Ready workspace。- 给宿主 agent 一个明确的下一步执行线索。
默认 workspace 会放在公开仓库外侧的相邻目录,避免把真实项目资料写进本仓库。
Agent 执行规则
ask 的输出不是最终答案,也不是让用户自己复制提示词。拿到推荐路线后,agent 要继续把事情办完:
- 如果需求已经明显属于某个 skill,agent 可以直接读取并调用该 skill,不必先让用户知道 skill 名。
- 如果只缺少输入材料或边界,agent 自己问最少的问题;用户补充后继续调用对应 skill。
- 如果使用了
ask,就把它当作路由和状态审计:按推荐 skill 读取SKILL.md,必要时读取该 skill 指向的 reference/template,然后直接产出结果。 - 如果
ask创建了 Project-Ready workspace,就把 workspace 当作长期项目记忆;后续产物写回对应的 decision、evidence、experiment、workflow 或 learning。 - 最终回复给用户的是本次任务的成果、下一步动作或需要确认的 Human Gate,不是“你可以使用某某 skill”。
什么时候用整个项目
用户想长期推进一个项目时,使用 GameDesignOS 项目模式:
python -m gamedesignos start "<项目名或一句话想法>"
它会自动准备第一条 Decision、Assumption、三分钟验证 Experiment、VOI Gate 和 Workflow Run。下一步只做终端输出里的那件事。
每个 Skill 单独怎么用
用户只想要一次性产出时,可以直接点名对应 skill;如果用户没有点名但意图已经明确,agent 自己选择并调用即可:
| 用户说法 | 单独使用 |
|---|---|
| 截图、录屏、PV、视频、商店页、试玩样本 | Use $game-experience-analyzer ... |
| 一句话游戏创意、玩法点子、核心循环、立项方向 | Use $game-concept-architect ... |
| 留存、首局、节奏、反馈、具身感、氛围、认知负荷、A/B、埋点 | Use $game-experience-density-optimizer ... |
| 商业策划案、独游设计案、pitch、GDD、vertical slice、决策 memo | Use $game-design-proposal-writer ... |
| prompt、workflow、schema、eval、router、memory、skill 改造 | Use $paranoia-ai-system-evolver ... |
| 英文游戏设计章节、术语表、长文翻译 | Use $game-design-book-translator ... |
| 文章、视频、作者、栏目、网站、知识库整理 | Use $game-design-source-curator ... |
如果不确定,先运行 python -m gamedesignos ask "<用户原话>",用它的推荐路线;如果会触发 Human Gate、发布、删除、真实账号、长期规则升级或项目范围锁定,再停下来问用户确认。
安全边界
- 不把用户真实项目资料提交到公开仓库。
- 不替用户接受 Human Gate、发布承诺、删除资产或锁定项目范围。
- 不把一次实验结果直接升级成长期规则;先保持 candidate。
- 不做镜像覆盖、批量删除、强制迁移旧 workspace。
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.
- 7d ago First seen · 69 lines · 972 tokens per session scan A 7a3b39697a81
GameDesignOS AGENTS.md is an instructions file published in the GitHub repository DY-2026/GameDesignOS (378 stars, last pushed 20d ago), licensed MIT. It adds 972 tokens to every session, about $0.0049 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.