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 smashup-faction-implementationgit 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/smashup-faction-implementation)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/smashup-faction-implementation"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/smashup-faction-implementation/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/smashup-faction-implementation"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/smashup-faction-implementation.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 | $0.00032 | $0.03522 |
| Opus 5 | $0.00016 | $0.01761 |
| Sonnet 5 | $0.00006 | $0.00704 |
| Haiku 4.5 | $0.00003 | $0.00352 |
Grade A, and why
smashup-faction-implementation 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 12d 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.
Smash Up 派系玩法实施工作流
适用范围
用于 Smash Up 新派系在 intake 完成后的正式玩法实施:运行时接入、ability / trigger / interaction / base ability 实现、共享机制复用、测试、E2E、evidence 和批量收口。本流程不重新裁定图片、atlas、资源真相源;这些属于 smashup-faction-intake。
进入 implementation 前必须已有 intake 合同和 handoff 包,至少包含主真相源、atlas 几何、row-major 索引、基地元信息、faction 清单、card/base canonical 名称、仍待裁定项和复用风险。intake 未收口时必须停下,不能边猜边做。
执行原则
- 连续推进:用户给出“长期任务 / 继续 / 不要停 / 最后再总结”时,默认清空当前 scope;硬阻塞才停,并写清剩余对象和卡在哪层。
- 一次一个派系:批量任务也按单派系闭环推进:实现、测试、E2E、evidence,再进入下一个派系;禁止多个派系同时改一半。
- 资源完成不等于玩法完成:atlas、locale、选派系入口、静态数据或单测通过,只能证明结构或展示接通;玩法完成必须包含玩法实现、测试、真实入口和 evidence。
- 先复用共享机制:优先查
src/games/smashup/domain/、src/games/smashup/abilities/、src/games/smashup/__tests__/是否已有 bury / uncover、ongoing modifier、movement、destroy、duel、before/after scoring、response window 等机制;确实缺共享抽象时再扩展共享层。 - 共享重构默认允许:确认共享抽象缺口后可直接做必要扩展,前提是服务当前和后续派系、不引入一次性硬编码、同步测试与 evidence,并说明影响范围。分支 / worktree / tag、删除本地数据等高风险动作仍需用户确认。
- 新派系 AI 走 outcome 合同:新增行动牌、可发动能力或其它会消耗手牌 / 次数 / 资源的对象时,AI 收益判断必须复用
game-ai-strategy-design的共享 outcome 合同和smashUpAiRuntime.projectActionOutcome;旧派系可按触碰范围逐步迁移,但新派系不得再为单卡补“零收益 / 无目标”特例。
批量重审模式
当任务是整批重审、重录或补证时:
- 建立批次对象清单,粒度到单卡、单基地或单 effect atom。
- 每项标注证据轴:
未核图 / 已核图 / 已修数据 / 已过最终状态 / 已过真实入口 / 已过生命周期。 - 用户说“继续”默认推进下一个未完成对象,不重复汇报上一个对象。
- 抽样发现 HIGH / CRITICAL、语义反转、ID 漂移、注册不触发或旧测试沿错语义时,旧“全面 / 收口”结论失效,必须回到全量矩阵。
- 批次清单仍有未完成对象时,只能写“仍有残余范围”。
effect atom 是重审最小单位。一张卡包含多个动作时,按目标选择、摧毁、额外打出、洗牌 / 重排等自然语义拆开;每个 atom 必须追到描述限定词、静态字段、command / validator、handler / reducer / trigger、UI / 交互出口、测试和证据。若测试断言沿错语义,测试本身就是 finding。
结论等级
对外汇报必须选择当前证据能支撑的等级:
结构审计通过:静态接入、注册、targetType、defId或结构测试通过;不证明玩法。代表性玩法已验证:有行为级测试和至少一条真实规则链路,但不是全对象覆盖。当前发布口径已收口:当前计划发布范围内,结构、行为、真实入口、生命周期和残余范围声明都闭合。仍有残余范围:仍有未审家族、共享根因、交互链或验证缺口。旧结论失效:旧 audit / rollup / closeout 被新证据推翻,必须回写原文档。
只说“审计 / 重审 / 收口审计”时,默认是对已锁定对象范围做对象级审计,不自动扩大到整批派系。只有所有对象都有对象级结论,或明确登记为共享链路完全同构、仅配置不同,才允许写“当前发布口径已收口”。
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.
- 12d ago First seen · 174 lines · 32 tokens per session scan A 20ae6bf69cd9
smashup-faction-implementation is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 3,522 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
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
threejs-qa-release
Verify and release Three.js browser games: playtest QA, automated bot playtests, mobile and responsive checks, production builds, static-hosting base paths, debug gating, bundle review, screenshots, visual regression baselines, canvas-pixel inspection with measured metrics, and release risk reports.
godot-e2e
Write and run E2E (end-to-end) game tests using the godot-e2e framework. Python controls a live Godot game over TCP — Locator-based semantic queries, expect() auto-retry assertions, and engine log capture make failures self-diagnosing. Use this skill whenever you need to: Test actual gameplay: player movement…
test-playable-web-games
Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.
visual-qa
Inspect Godot screenshots or short frame sequences for acceptance issues. Use after capturing a scene, when checking camera framing, missing assets, UI overlap, collision visualization, animation, or a black/empty viewport.
pie-testing
Start, stop, and query Play-In-Editor (PIE) sessions for runtime testing of Blueprints, gameplay logic, widgets, AI, and any in-game behavior. Use when the user asks you to "play", "test", "run", "PIE", "start/stop the game", or otherwise needs a live game world to validate changes.