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 mage-wars-ui-design-memorygit 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/mage-wars-ui-design-memory)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/mage-wars-ui-design-memory"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/mage-wars-ui-design-memory/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/mage-wars-ui-design-memory"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/mage-wars-ui-design-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.14137 |
| Opus 5 | $0.00030 | $0.07068 |
| Sonnet 5 | $0.00012 | $0.02827 |
| Haiku 4.5 | $0.00006 | $0.01414 |
Grade A, and why
mage-wars-ui-design-memory 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 4d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mage Wars UI Design Memory
这是 BoardGame 项目内、Mage Wars 设计稿与真实 Board/UI 实现专用的用户纠偏索引 / drift-check。它只记录 Mage Wars 的具体对象、素材职责和用户纠正实例；通用 UI、响应式、动效、E2E、看图和审计方法均以 .spec/knowledge/standards/ 与对应项目 skill 为准，本 skill 不承载这些规范正文。
角色与优先级
- 本 skill 的角色是
drift-check / evidence，不是canonical-source。它只能提醒 Mage Wars 专项对象是否被漏掉、职责是否混淆、送验前是否踩过用户纠正项。 - 多端布局、PC/移动同构、手机横屏、是否新增移动专用承载，以
.spec/knowledge/standards/ui-responsive-layout.md为唯一规范正文；不得用本 skill 的底部空间、槽位分离或基础布局自审条款覆盖它。 - 可见 UI 改动门禁以
.spec/knowledge/standards/ui-change-gates.md为准；通用 UI/UX 以.spec/knowledge/standards/ui-ux.md为准；动效和特效以.spec/knowledge/standards/animation-effects.md为准；E2E 与截图证据以.spec/knowledge/standards/e2e-verification.md为准。 - 用户开图由项目
show-image-to-userskill 决定，正式图面审计由项目ui-audit-loopskill 决定。本 skill 不授权“每轮截图 / 每轮打开图片”，也不把技术截图落盘解释成可送人工验收。 - 若本 skill 的历史措辞能被解读为要求改布局、改移动端界面锚点、新增承载或顺手重构，应先回到上述规范裁决；确认冲突时修正或删除本 skill 的问题措辞，而不是在更下层加反向覆盖。
使用顺序
- 先按
.spec/knowledge/README.md选择本轮真正命中的规范正文；涉及 PC/移动、横屏、响应式或承载变化时，必须先读ui-responsive-layout.md。 - 当前任务确实涉及 Mage Wars 设计稿、真实 Board/UI、用户标注图或送验自审时，再读本 skill 作为专项 drift-check。
- 锁定用户当前指出的具体对象，不要把一个局部问题扩大成整套 UI 重排，也不要把特效、技能流程或 E2E 修复顺手升级成界面锚点 / 移动布局改版。
- 改 Open Design artifact 前，写一段“用户原话 -> 本轮动作”的自审；若本轮不是设计稿 / UI 布局任务，只记录风险或后续项，不直接重构布局。
- 改 Open Design artifact 前，先更新并消费
docs/games/mage-wars/design/reference/user-correction-traceability-ledger.md；它是本主题的纠正覆盖账本 / drift-check，不是独立规范来源。 - 出图后，按当前任务合同、上位规范、“用户原话反思表”和纠正覆盖账本逐条判定
PASS / REVISE；有任一条犯错，不得送人工验收。 - 用户可见交付默认给图：Open Design 截图、草稿图、标注图或真实 UI 截图；是否打开、何时打开、打开哪些图，必须服从项目看图和 UI 审计规范。规则对象覆盖矩阵、纠正账本和自审结论只作内部证据或最终极短回执。
规则到 UI 到实现执行顺序
本节只在 Mage Wars 设计稿、真实 Board.tsx / UI 实现、实现截图送人工验收这三类任务中作为专项检查表使用。它约束“规则对象是否被正确承载”，不替代通用 UI、响应式、动效、E2E 或看图规范；任何一段都不得只看最后一张图或只看 E2E 结果。
- 先锁规则对象
- 当前轮次重新读取规则真相源、素材 / atlas 合同、区域锚点合同和本 skill。
- 写出本轮画面里每个规则对象的现实职责：当前主对象、仍可用候选、可浏览归档、隐藏信息或程序化运行态 UI。
- 规则没有的概念不得进入 UI 文案、class、aria、审计或汇报；用户口语里的“手牌”只在解释时映射为规则术语
法术书，不得上屏。
1.5. 建立规则对象覆盖矩阵
- 任何 UI 设计、Open Design artifact、真实
Board.tsx实现或实现截图送验前，必须先建立或更新规则对象 -> UI 承载覆盖矩阵；不能只靠最后一张图或用户纠正账本倒推有没有漏项。 - 当前项目默认落点是
docs/games/mage-wars/design/implementable/rule-to-ui-element-list.md；它负责把规则、TTS / Workshop、atlas 和素材合同提炼为布局、交互和 UI 元素输入。运行时截图覆盖表只能作为 evidence / drift-check，不能替代这份设计前置清单。 - 每一行至少写清：规则对象、规则真相源、当前阶段职责、默认可见性、实体锚点、玩家可执行动作、素材来源 /
approved-programmatic-runtime-ui裁定、截图验收方式。 - Mage Wars foundation 最低覆盖行包括：2x3 竞技场区域、法师战场实体、玩家 / 法师提示卡、法师牌详情 / 规则回看入口、双方学徒法师生命 24 / 法力 / 聚魔、己方法术书 6 张、己方已计划法术 2 张、对手已计划卡背、公开弃牌堆正面 + 数量 + 展开入口、隐性结界 / 隐藏信息卡背、攻击骰、效果骰、伤害状态 / 伤害数值、燃烧 token、守卫 token、行动 token、来源对象、合法目标高亮、可移动区域高亮、当前阶段 / 当前动作、回合结束入口。
- 矩阵中的每一行必须有明确结论：
visible、collapsed-with-visible-entry、hidden-by-rule、out-of-scope、blocked或approved-programmatic。没有结论的对象按遗漏处理，当前稿不得AI_PASS。 - 用户纠正账本里的每一条纠正必须回指到矩阵中的至少一行；若找不到对应规则对象，先补规则对象裁定，再改设计或实现。
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.
- 4d ago Changed · +1 lines 3d2121f5f9d4
- 5d ago Changed · +2 lines 5a21badb520f
- 6d ago Changed · +12 lines 39e6b1cae4ff
- 12d ago First seen · 179 lines · 60 tokens per session scan A e7926f860bbb
mage-wars-ui-design-memory is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 14,137 once invoked, about $0.0003 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
roblox-ui
Build production Roblox interfaces with ScreenGui/PlayerGui lifecycle, responsive UDim2 layouts, safe insets, reusable editable Instances, cross-device input and selection, restrained motion, cleanup, and multi-viewport verification. Use for Roblox HUDs, inventories, shops, settings, ability bars, ScrollingFrames…
game-ui-ux
Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a screen/menu state stack, and event-driven (not polled) HUD updates. Engine- neutral patterns that pair with the detected…
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
ux-review
Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.
unity-inspector
Advise on Unity Inspector authoring UX.
threejs-game-ui-designer
Design premium Three.js game UI: HUDs, menus, overlays, pause/win/lose screens, settings, icon controls, touch UI, typography, responsive layout, safe areas, text fit, and UI/world cohesion.