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 feedback-closeoutgit 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/feedback-closeout)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/feedback-closeout"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/feedback-closeout/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/feedback-closeout"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/feedback-closeout.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 | $0.00046 | $0.03873 |
| Opus 5 | $0.00023 | $0.01937 |
| Sonnet 5 | $0.00009 | $0.00775 |
| Haiku 4.5 | $0.00005 | $0.00387 |
Grade A, and why
feedback-closeout 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
反馈收口
单一真相
本 skill 是 BoardGame 反馈收口 workflow 的唯一规范真相源。references/feedback-open-api.md 只描述 HTTP 接口；服务器、SSH 和 Mongo 入口按根 AGENTS.md 指向的共享用户环境文档读取。
临时材料只作证据或镜像：
temp/feedback-closeout/**evidence/feedback-closeout/**- 截图、诊断包、导出文本
temp/feedback-closeout/status-board.json
这些都不能冒充本地数据库当前状态，也不能冒充线上正式反馈记录。
默认口径
用户说“处理反馈 / 收口反馈 / 修复反馈”且没有明说线上、生产、远端、真实反馈或回写线上时，默认目标是本地数据库反馈记录。
| 口径 | 真相源 | 允许写哪里 | 禁止 |
|---|---|---|---|
| 本地数据库 | 本机反馈数据库或本地开发 API | 本地数据库 + 本地状态镜像 | 自动拉线上或说成线上已回写 |
| 线上真实 | 线上真实反馈接口或经确认的线上真实写入口 | 线上真实记录 + 本地状态镜像 | 用本地导出替代线上记录 |
| 离线快照 | 用户明确指定的导出、诊断包或本地文件 | 指定文件 / 状态板 | 说成本地数据库或线上当前状态 |
找不到本地数据库入口时，停在“缺少本地数据库反馈来源”；不要自动改拉线上替代。
完成门槛
- 目标范围内仍有
open / in_progress / resolved任一未收口项时，不得宣称完成。 - 数量多不是停止理由；继续批量处理直到清零，或报告真实阻塞。
- 每次阶段汇报和最终汇报必须写清口径和绝对时间。
- 对用户展示问题时，以“反馈内容 / 现实症状”为标题；反馈 ID 只放追溯证据，不作为主标题。
- 玩家反馈要写清游戏中文名、命中的对象 / 页面 / 效果、规则本应发生什么、实际坏在哪条玩家可见链路。
- 玩家反馈命中卡牌、技能、状态、基地、教程步骤或其它规则效果时，必须同时给出“效果描述原文”：从本轮确认的规则书、牌面图、录入合同、运行文案或其它真相源逐字摘出对应效果文本，并标明来源；不能只给实现摘要、测试名或自己的改写。
- 每条真 bug 反馈收口前，必须补“漏审复盘 / 规范回代判断”：旧测试、旧审计或旧规范为什么没挡住；属于已有规范未执行、规范缺口、测试缺口、审计留档缺口还是单游戏合同问题；若需要更新规范，写清唯一真相源并同轮更新，若不需要，写清哪条现有规范已经覆盖。
- 系统自动反馈要写清自动检测场景、现实影响、监控触发条件、止血动作和根因证据是否存在。
处理顺序
默认优先级是人类反馈 > 系统自动反馈。系统单可以作为并行止血支线，但不能因为更容易查或数量更多挤占人类反馈。
系统自动反馈即使暂缓，也必须先做最低分诊：
- 自动反馈类型；
- 错误消息；
- 状态快照 / 行动日志里的原因；
- 当前是否存在 interaction、legal actions、AI decision preview；
- 是否属于共享 / 私有视图不一致、0 个合法动作、恢复 / 跳过被拒绝、或基础设施告警。
基础设施告警只有重启、恢复、阈值和采样证据时，只能说已止血 / 已恢复；没有 profiler、堆栈、房间 / 请求关联或循环位置证据，不得称为根因已定位。
工作流
- 定位来源：先确认本轮口径和真实读写源；线上口径必须确认接口返回反馈 JSON 而不是前端 fallback HTML。
- 排重归并：按内容和错误签名归并重复组，只处理代表项。
- 分类：至少分为
bug_candidate、non_bug、needs_owner_decision、needs_review。 - 检查近期状态：先看本轮口径下该反馈是否已经
resolved / closed，再看本地镜像、历史 evidence 和最近相关代码 / 测试，避免重复修。 - 分诊真假 bug：先锁反馈真实症状、真相源和可复现链路；若反馈涉及规则 / 卡牌 / 效果，先摘出效果描述原文并对照当前实现，再决定是否改代码。
- 修复与验证：真 bug 必须有修复、匹配验证和证据；误报 / 建议 / 已失效只写结论，不改代码。
- 漏审复盘与规范回代：真 bug 修完后按
regression-closeout.md反思旧测试 / 旧审计 / 旧规范为什么没挡住，并明确本轮是否更新规范；需要更新时先锁canonical-source，不能把结论只留在对话或 evidence。 - 立即回写：接手即写
in_progress；结论成立即写resolved / closed，并同步本地状态镜像。 - 回查收口：最终回复前回查本轮口径下的真实状态和本地镜像。
- 用户决策门：只要反馈本体没有被证明解决，或下一步需要用户判断，必须保留为
in_progress，并在汇报中先逐字给出真实反馈原文（保留换行、标点和语气），再给证据和待判断事项；不得把“证据不足 / 未证实 / 需要判断”直接回写成closed。
What ships with it
11 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.
- agents/openai.yaml 353 B
- references/feedback-open-api.md 2.0 KB
- scripts/finalize-feedback-group.mjs 6.5 KB runs code
- scripts/lib/feedback-status-writer.mjs 14 KB runs code
- scripts/lib/feedback-status-writer.test.mjs 9.0 KB runs code
- scripts/lib/status-board.mjs 11 KB runs code
- scripts/lib/status-board.test.mjs 7.4 KB runs code
- scripts/sync-feedback-status-board.mjs 1.1 KB runs code
- scripts/triage-open-feedback.mjs 16 KB runs code
- scripts/update-feedback-status.mjs 5.6 KB runs code
- scripts/update-local-feedback-board.mjs 3.3 KB runs code
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 · +16 lines 93a4c94dad3a
- 11d ago First seen · 176 lines · 46 tokens per session scan A c25873ef7fdb
feedback-closeout is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 3,873 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
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.