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 rule-bug-fix-workflowgit 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/rule-bug-fix-workflow)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/rule-bug-fix-workflow"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/rule-bug-fix-workflow/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/rule-bug-fix-workflow"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/rule-bug-fix-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Agent Snooping · line 24 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 25 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00050 | $0.01797 |
| Opus 5 | $0.00025 | $0.00898 |
| Sonnet 5 | $0.00010 | $0.00359 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
rule-bug-fix-workflow 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 5d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
规则 Bug 修复流程
路由边界
本 skill 已是规则 bug 的执行入口；不要再先回读 game-audit-workflow/references/reading-map.md 形成循环路由。
本 skill 只负责规则 bug 的执行顺序；规则合同、交互权限、回归收口和审计口径仍以 .spec/knowledge/README.md 命中的主源为准。
如果当前目标不是规则 bug，或用户要求“全面审计 / 为什么审计没审出来 / 审计收口”，再进入 game-audit-workflow/references/reading-map.md 重新分流。
按需读取
默认读取：
- 合同门禁：.spec/knowledge/standards/rule-contract-audit.md。
- 回归收口：.spec/knowledge/standards/regression-closeout.md。
按命中情况追加：
- 反馈涉及响应窗口、阶段按钮、结算攻击、结束防御、视角 / 焦点玩家、AI 合法动作或自动推进：读取 .spec/knowledge/standards/rule-driven-interaction-design.md。
- 用户要求“全面审计 / 为什么没审出来”：进入 .spec/skills/game-audit-workflow/SKILL.md，由其 reading-map 选择描述到实现、证据模板和回归收口主源。
- 规则合同缺失、图片/卡图/规则书冲突或对象归属未锁：进入 .spec/skills/data-entry-workflow/SKILL.md，并读取 .spec/knowledge/standards/data-entry.md。
- 反馈涉及真实 UI 入口、按钮、提示、截图或 E2E：读取 .spec/knowledge/standards/e2e-verification.md，必要时读取 .spec/knowledge/standards/ui-change-gates.md。
- 只需要命令、状态注入、骰子/随机数或 TestHarness API：读取 docs/testing-tools-quick-reference.md；项目脚本目录查 docs/tools.md。
- 入口不明确：回 .spec/knowledge/README.md，不要自行拼接一套阅读清单。
判层
跨游戏判断方法：锁症状、查合同、判实现消费、回写合同、补回归、同类扩审。当前单游戏答案：具体卡牌原文、技能等级差异、骰面公式、图标裁定、结算数字。单游戏答案下沉位置：docs/games/<gameId>/...事实资料、对应 evidence、用户故事、规则矩阵或该游戏自己的项目 skill。
禁止把当前游戏的专属规则答案写进项目通用层。
执行顺序
- 锁原始症状
- 写清反馈断言指向哪个对象、哪个等级/版本、哪个状态并存、哪个时机、哪个最终结果。
- 反馈断言包括对话描述、线上反馈记录、截图/红圈标注、日志解释、测试观察和交接摘要里的 bug 表述；它们都只是待核对输入，不是自动真相。
- 不得把排查中发现的外围异常替换成本轮目标。
- 用户用疑问句追问截图、界面现象或阶段画面时，先回答“图上哪些是规则说明、哪些是真实可操作对象、当前设计是否符合规则”。这不是 UI 改造授权；只有证据证明规则结算或真实交互确实错了，或用户明确要求改界面，才允许新增、删除或重排玩家可见 UI。
- 找已有录入合同
- 先查规则文档、录入表、evidence 子句表、user story、静态数据和当前描述。
- 判断合同是
locked / blocked / disputed / 未找到。 - 必须先把反馈断言与当前技能/卡牌/Token/状态描述逐项比对；反馈断言不是自动真相，当前描述也不是免检真相。
- 先提炼规则结构
- 把规则源拆成基础对象、触发条件、玩家选择、状态变化、抽牌 / 掷骰 / 移动 / 结算结果、结束条件。
- 图标、颜色、牌型、房间标记、阵营可见性、次数限制等必须落成结构化字段，不能只留在长文、图片或教程文案里。
- 如果规则源已有字段但当前 catalog / 静态数据 / 合同表没有对应字段，先标
needs-contract或implemented-needs-remodel；不得用运行时轮换顺序、默认值、旧实现习惯或泛化文案顶替。
- 判断是不是实现消费错误
- 合同
locked且实现与合同冲突：按实现 bug 处理。 - 反馈断言与当前合同一致：优先检查实现是否正确消费合同，不要先重看图片。
- 反馈断言与当前合同不一致：先回图面、规则书或录入真相源复核；确认合同错了再修合同和实现，不得直接按反馈断言改规则逻辑。
- 合同缺失、冲突或反馈断言与合同冲突：回
data-entry-workflow复核，不得直接改规则逻辑。
- 合同
- 拆原子断言
- 至少拆出触发时机、可选/必须、资源消耗、状态授予/消费、伤害或最终状态、基础版/升级版差异。
- 对“同时拥有多个状态”“先后结算”“低数值边界”“已持有状态再获得状态”必须单列断言。
- 最小修复
- 优先修直接消费点、共享 helper 或时序根因。
- 若根因是共享抽象错误，必须扩到共享层修；不得只给单对象打补丁。
- 同步合同入口
- 同步中文/英文描述、能力定义注释、升级版描述、测试断言、evidence 或用户故事。
- 旧错误描述未清干净时，不得说规则 bug 已收口。
- 补回归验证
- 引擎/规则问题至少补单测或 GameTestRunner 断言。
- UI 入口问题按
.spec/knowledge/standards/e2e-verification.md决定是否需要 E2E 与截图。
- 同类扩审与漏审复盘
- 查同名基础版/升级版、同族对象、共享 helper、同一状态字段、旧测试和旧 evidence。
- 写清为什么这次旧审计或旧测试没挡住；必要时更新通用规范或单游戏文档。
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.
- 5d ago Changed · +2 lines d4f6682c2405
- 11d ago First seen · 91 lines · 50 tokens per session scan A 3c67328025c1
rule-bug-fix-workflow is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,797 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
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
graphics-api-hooking
Analyze Direct3D/DXGI, OpenGL, and Vulkan rendering, presentation, composition, and capture evidence. Use to distinguish API samples, PresentMon event metrics, Tracy instrumentation, compatibility translation, frame images, and validation diagnostics; review swap chains, overlays, resource lifetime, and…
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.
console-clear-logs
Clear the MCP log cache (used by 'console-get-logs') and the Unity Editor Console window. Useful for isolating logs to a specific action by clearing the slate first.
profiler-start
Enable Unity's runtime profiler and open the Profiler window. Idempotent: calling when already enabled returns the current enabled state without error.