Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zhuanggenhua/BoardGamenpx agentmods add skills/zhuanggenhua/boardgame/dicethrone-hero-intakeWrote 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/dicethrone-hero-intake)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/dicethrone-hero-intake"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/dicethrone-hero-intake/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/dicethrone-hero-intake"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/dicethrone-hero-intake.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 | $0.00036 | $0.05032 |
| Opus 5 | $0.00018 | $0.02516 |
| Sonnet 5 | $0.00007 | $0.01006 |
| Haiku 4.5 | $0.00004 | $0.00503 |
Grade A, and why
dicethrone-hero-intake 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 yesterday.
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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dice Throne 角色图片录入工作流
适用范围
用于 Dice Throne 单个角色或一批新英雄的 intake：锁真相源、裁图、录入玩家板 / 提示板 / 骰面 / Token / 能力 / 卡牌、同步 i18n 和规则文档、重建 manifest、上传资源、补测试与 evidence。本流程只负责“已有素材与规则材料的正确录入”；复杂机制设计另走规则实现 workflow。
输入与真相源
最低输入：
player-board、tip、ability-cards、dice原图或等价骰面来源。- 角色英文 canonical 名称来源。
- 角色对照源：官方规则书、官方 PDF、Wiki、FAQ 或用户指定来源。
- FAQ 裁定源：
docs/games/dicethrone/sources/faq/王权骰铸常见问题总览2.1.1.docx。
第一优先级：完整数据录入
Dice Throne 角色 intake 必须先完成数据录入，再进行资源接线、卡牌描述同步或机制实现。实际打开、读取、OCR、裁切或抽样过的 player-board、tip、ability-cards、dice、Token / 状态图标和其它图片，都必须进入图片登记表；无论最后是否进入运行时，都要记录图面数据、对象 / 槽位、最终处置（runtime / reference / duplicate / excluded / blocked）和处置依据。不能用“这张图只是参考”或“看起来没用”代替登记。
完整录入的唯一通用定义来自 data-entry.md 的完整语义录入门禁。Dice Throne 录入时必须特别枚举：
- 费用角标、卡牌类型条、攻击 / 防御 / 终极伤害标识、伤害框色和其它具有规则分类含义的颜色或边框。
- 每个骰面图案、骰面名称、重复骰面数量，以及骰面与技能条件、奖励或分支的对应关系。
- Token / 状态图标、层数、获得 / 消耗 / 移除方式，以及图标、数字和正文对应的对象。
- 标题、副标题、正文段落、脚注、图中标签和“此外 / 每有 / 每层 / 否则 / 至多 / 仅 / 不能 / 然后”等会改变数量、范围、条件、例外或顺序的限定词。
- 升级牌上下子区、箭头、覆盖关系、相邻关系、区域顺序，以及一个数值、图标或颜色究竟修饰哪个技能或子句。
以上元素不因当前代码没有字段、当前 UI 不展示、当前测试未覆盖或当轮暂时用不上而省略；先完整记录，再标 consumed / reference / deferred / not-currently-consumed / blocked / disputed。无法证明纯装饰时不得直接丢弃。
角色锁定录入合同后，卡牌名称和描述、i18n、运行时卡牌 / 能力定义以及机制实现只能消费这份合同。任何消费方与合同不一致，都必须先回到录入合同和主真相源修正，再修消费链并重新审计。
权威分工：
- 汉化图 / 用户指定图：中文名、中文描述、图内顺序和裁图定位。
- 官方规则书 / PDF / 官方图：英文与规则裁定高优先级对照。
- FAQ：补充状态花费 / 移除、响应窗口、攻击是否成立、防御是否可用等边界；不替代图面主真相源。
- Wiki / Fandom / Rulepop：只能辅助英文名或冲突发现；若转成本地快照，必须保留来源链接和获取日期。
- 当前 worktree：本轮资源、裁图、manifest、发布结果和测试证据的唯一执行现场。
冲突处理：
public/assets/i18n/zh-CN/dicethrone/images/<hero>/compressed/ability-cards.webp或正式同源 atlas 是卡牌语义主真相源；temp/dicethrone-intake/<hero>/...里的裁片只辅助读字。- 用户口径、实现、i18n、测试快照或旧 evidence 任意两者冲突时，先回完整单卡、玩家板或提示板重录合同；不得把用户随口词直接写成官方卡名、分支名、规则字段或测试期望。
- 重新录入前必须先有最小字段合同：对象、正式图源、atlas/index 或槽位、单对象裁图、图面原文、分支 / 槽位结构、当前实现差异和合同状态。
玩家板与槽位合同
只要玩家板能看出技能槽、被动槽、防御槽、终极槽、展示槽或空槽，录入阶段必须建立 玩家板图面合同：
- 逐槽记录物理坐标、图面标题、运行时对象、允许状态和是否可交互。
slotId只表示物理位置，不能表示技能名；共享坐标不等于共享技能语义。- 覆盖层、点击反查、高亮反查和测试断言必须消费同一份
当前英雄 + 物理槽 -> 玩家板图面技能合同。 - 升级牌覆盖槽位必须对齐三件事：运行时
replaceAbility(targetAbilityId)、升级牌中文名、玩家板中文槽位标题。缺任一项只能标blocked / disputed。 - 发现升级牌盖错槽、点错槽或和底图标题不一致时，必须横扫同英雄、同批次和同一共享槽位消费链：全部替换型升级牌、覆盖槽 helper、点击 / 高亮反查槽和真实升级稳定态。
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.
- yesterday Changed · +11 lines e1728e905617
- 7d ago Changed · +2 lines 90c42172b7c4
- 12d ago First seen · 219 lines · 36 tokens per session scan A 4dd471f46bd6
dicethrone-hero-intake is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 5,032 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.