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 zhuanggenhua/BoardGame --skill game-ai-adaptationgit clone --depth 1 https://github.com/zhuanggenhua/BoardGameWrote 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/zhuanggenhua/boardgame/game-ai-adaptation)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/game-ai-adaptation"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/game-ai-adaptation/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/zhuanggenhua/boardgame/game-ai-adaptation"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/game-ai-adaptation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 166 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00046 | $0.02363 |
| Opus 5 | $0.00023 | $0.01182 |
| Sonnet 5 | $0.00009 | $0.00473 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
game-ai-adaptation 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game AI Adaptation
本 skill 只管 AI 合法动作、交互闭环、卡死和兜底；AI 打法强弱、评分器、角色画像和策略重构走 game-ai-strategy-design。
触发
出现以下任一情况必须使用：
- 修改
src/games/<gameId>/ai.ts。 - 新增或修改自动响应、自动跳过、强制结束、watchdog。
- 修 “AI 卡死 / 无法选择 / 重复交互 / 跳过后重触发 / 响应音效循环”。
- 新游戏接 AI，需要审查交互闭环与兜底。
- 玩家真实交互合同改变，例如确认入口、对象选择路径、阻塞层生命周期、弹窗承载物或收口按钮迁移。
必读
engine-systems。testing-audit。references/checklist.md。references/response-window-watchdog.md。references/vitest-templates.md。
历史 evidence 只能作同类参考；不能代替本轮真实链路审计。
本仓库 AI 执行链
Interaction 链
- 游戏层通常在
domain/execute.ts或domain/systems.ts创建交互。 - 引擎层
InteractionSystem承接sys.interaction.current / queue、choice 创建、resolve 和playerView()。 createSimpleChoice()拿到空 options 是卡死前兆，不是可接受状态。- 非 owner 在
playerView()中可能只看到isBlocked=true；sharedState 看不到 current 不等于没有交互。
Response-window 链
ResponseWindowSystem负责打开 / 关闭响应窗口、RESPONSE_PASS、强制关闭、允许命令和 responder 门禁。- 响应窗口能否闭合，取决于是否有合法响应、无响应 pass、不会因 stale queue / reopen 再卡住。
- 必须区分：
- human 自己回合且 human 在响应：watchdog 不得出手。
- AI 当前阶段被 human 响应窗口卡住：watchdog 可先强制关闭窗口，再继续 AI 阶段收口。
- AI 自己是 responder：AI 可发合法响应或
RESPONSE_PASS。
在线 AI 兜底链
- 服务端 watchdog 在
src/engine/transport/server.ts。 - AI 恢复逻辑在
src/engine/transport/onlineAiRecovery.ts。 - watchdog 是 AI seat 专属兜底，不是全局强推。
- hidden interaction 必须用
applyPlayerView(match, playerId)生成 seat view 后诊断。
核心合同
1. AI 只能选合法动作
- AI legal actions 必须和
validate()/execute()同源一致。 disabled=true、已失效目标、不可移除状态、已确认阶段的旧动作不得进入 AI 动作。- legal actions 为空时，必须走 cancel / pass / skip / advance 之一；不能继续等。
- 真人在同一规则状态下能选择的并列合法动作，AI legal actions 也要枚举；策略不想选时在评分层降权，不在合法动作层删掉。
2. 每个交互必须可收口
每个 AI 相关 interaction / response-window 至少有一个正式收口路径：
SYS_INTERACTION_RESPONDSYS_INTERACTION_CANCELRESPONSE_PASSADVANCE_PHASE- 游戏特化阶段推进命令
没有收口命令是设计缺陷，不是“之后靠 AI 补”。
3. UI 交互合同变更要同步审 AI
What ships with it
4 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.
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 Changed e8762dcd4034
- 12d ago First seen · 174 lines · 46 tokens per session scan A 467affedd18d
game-ai-adaptation is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 2,363 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.