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 ui-audit-loopgit 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/ui-audit-loop)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/ui-audit-loop"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/ui-audit-loop/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/ui-audit-loop"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/ui-audit-loop.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 | $0.00114 | $0.07586 |
| Opus 5 | $0.00057 | $0.03793 |
| Sonnet 5 | $0.00023 | $0.01517 |
| Haiku 4.5 | $0.00011 | $0.00759 |
Grade A, and why
ui-audit-loop 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 10d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Audit Loop
把 UI 验收当成独立门禁。代码正确、元素存在、点击成功和 E2E 通过都不能单独证明玩家看到的界面合格。
用户可见图验收触发口径
截图 / 录屏审计和打开图片 / 录屏是稳定交付候选的最终验收动作，不是每次过程性 UI 修改的默认门禁；换句话说，开图或开录屏是完整重构或稳定候选完成后的胜利号角，不是实现过程中的例行动作。只有当本轮 UI 已经完成到可以宣称“可验收 / 可交付”、用户明确要求截图验收/玩家视角检查/打开图/录屏，或测试虽通过但界面仍存在高风险可用性疑点时，才进入本循环。
仍在搭建框架、跑通功能链、修流程、处理临时测试界面、占位 UI，或后续步骤会继续改造同一界面时，只做与当前风险匹配的功能、结构或局部截图 / 录屏诊断；不得因为改了可见 UI 就主动把中间图或诊断录屏当作最终验收物打开给用户。等完整重构完成并形成稳定候选后，再按本 skill 产出真实入口截图 / 录屏、AI 图面裁决和用户可见最终图 / 录屏。
新交互 / 新 UI 的端到端覆盖要求由 .spec/knowledge/standards/e2e-verification.md 与 .spec/knowledge/standards/ui-change-gates.md 维护；它要求覆盖矩阵和真实页面 E2E，但不等于每轮都打开图片、录屏或重跑全量截图。进入本 skill 时，只处理稳定候选或用户明确要求的图面 / 动效审计；用户可见展示仍必须等同一组图或录屏明确 PASS 后才允许。
- 先 AI 验，再给用户验：助手必须先检查原始最终候选截图 / 录屏做玩家视角审计，明确写出图面 / 动效事实、
PASS/REVISE结论、失败点或通过理由。用户已明确要求“打开图 / 录屏”但当前尚未PASS时，不得展示；继续审计或返工。不得先产生 PureRef / 系统查看器 / Codex 内联图 /view_image/Viewed Image等用户可见事件，再把它冒充验收。 - 验收范围只限本轮要求（强制）：进入截图验收时，先把用户本轮明确要求拆成可判定清单，例如“推斥必须看到来源唤醒 / 飞行路径 / 命中帧”“传送必须看到来源轨迹落点”“截图说明必须中文”。
PASS只要求这些清单项全部达标。不要把整页 UI、其它系统、非目标布局缺陷或历史未完成项塞进本轮硬门禁；它们只能作为备注，除非它们直接让本轮清单项无法被截图证明。反过来，E2E 绿、像素亮点、文件存在或其它非目标证据，也不能替代清单项本身达标。 - 未解决本轮问题禁止开图（强制）：如果用户刚指出的问题本身还没有直接证据证明已解决，不能因为“其它 UI 通过”“E2E 通过”“截图已经生成”“只是想让用户看一下”而开图。开图门禁只问本轮要求有没有逐条达标；非本轮问题不升级为阻塞，非本轮通过项也不计入达标。
- 用户可见展示只在触发后执行：当用户明确要求看图 / 打开图 / 截图验收 / 录屏，或本轮交付物本身就是图片型验收图 / 动效验收录屏时，同一张原始验收图、同一组原始验收图或同一份录屏被选为最终候选且 AI 判定
PASS后，必须交给项目show-image-to-user入口展示，再汇报完成。若本轮只是补 evidence、盘点截图 / 录屏、汇报测试或记录核图结论，未触发用户可见展示时，只汇报路径和结论，不自动打开查看器。 - 不通过就循环：只要 AI 判定
REVISE，且失败项属于当前 UI 目标范围，就继续改同一实现、回同一真实入口重拍、重新审计；不得把失败图交给用户人工挑错，也不得等用户催促才继续。 - 流程 UI 默认多图：如果 UI 改动涉及进入、选择、投掷、翻页、展开/关闭、前后状态、PC/移动对照或完整链路，最终验收物默认是有序截图集，而不是只给最新一帧。每张图必须说明它证明哪一步。
- 动效验收通过后优先录屏展示：如果本轮验收对象是召唤、攻击、投射物、伤害飘字、拖拽、翻页或其它连续动画，关键帧截图仍用于 AI 自检和证据定位；当用户明确要看实际效果且本轮清单已
PASS后，最终用户展示优先使用短录屏 / GIF，而不是让用户从多张静态截图推断动作连贯性。录屏只证明它覆盖的那段动作，不能替代未录到阶段的验收。 - 联系表不能替代逐图审计：contact sheet、拼图、缩略图或低清总览只能用于索引和初筛；涉及目标选择、对象可读、遮挡、候选高亮、按钮归属或多步流程时，必须用不向用户展示的方式逐张检查对应原始截图。没有逐图检查原图，就不得输出
PASS或把该图放入最终验收集；如果当前宿主没有私有看图能力，只能停在证据不足或补非展示型机器检查，不能先把未通过图打开给用户。 - 阻塞口径：如果真实入口、截图生成、素材加载或图面审计被环境阻断，只能按阻塞汇报，说明现实后果、证据、为什么阻止继续、最小补救动作；不得宣称 UI 已完成。
What ships with it
5 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.
- 10d ago First seen · 172 lines · 114 tokens per session scan A e0f8a0cf75ce
ui-audit-loop is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 7,586 once invoked, about $0.0006 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
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
design-qa
Internal prototype QA helper. Use only after a Product Design prototype, URL-to-code build, or image-to-code build has a source visual target and a rendered implementation to compare before handoff. Do not use for broad UX critique, design critique, product audits, or flow reviews; route those user-facing requests to…
health
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…
hunt
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code…
ui-craft-checks
Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…