Borrowing it
Nothing to install: this file belongs to banbanzhige/ai-goofish-monitor-QB. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/banbanzhige/ai-goofish-monitor-QB/master/AGENTS.mdgit clone --depth 1 https://github.com/banbanzhige/ai-goofish-monitor-QBWrote 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/instructions/banbanzhige/ai-goofish-monitor-qb/agents-md)<a href="https://agentmods.dev/instructions/banbanzhige/ai-goofish-monitor-qb/agents-md"><img src="https://agentmods.dev/badge/instructions/banbanzhige/ai-goofish-monitor-qb/agents-md/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/instructions/banbanzhige/ai-goofish-monitor-qb/agents-md"><img src="https://agentmods.dev/badge/instructions/banbanzhige/ai-goofish-monitor-qb/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01169 | $0.01169 |
| Opus 5.5 | $0.00468 | $0.00468 |
| Sonnet 5.5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
ai-goofish-monitor-QB AGENTS.md 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 1mo 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.
What it actually says
1. 目标与边界
本仓库是 闲鱼监控与 AI 推荐项目(ai-goofish-monitor-QB)。 核心链路:监控抓取 → 条件筛选 → AI / 贝叶斯分析 → 结果存储与展示 → 通知推送。
关键原则:
- 新增 Windows x64 便携版,内置 PostgreSQL 和独立 Launcher;保留现有 Docker 构建与部署路线,便携版不依赖 Docker。
- 公开发行、持续迭代,欢迎社区贡献;不擅自改变抓取频率、用户数据隔离、AI 调用和通知行为。
- 最小改动优先(避免无关重构)。
- 启动器、基础配置、状态和更新规划以
docs/PORTABLE_LAUNCHER_PLAN.md为交接基线;规划不等于已实现。 - 用户已暂停许可证调整,继续保留当前
License的 MIT 许可。此前 GPL 切换讨论不再是执行指令;未经用户重新提出,不推进换证、非商用限制或贡献重授权,也不将其作为启动器开发阻塞项。 - Launcher 技术路线已确认为 C# / Avalonia UI / 自包含 .NET;首期只交付 Windows x64。编排核心与平台适配隔离,不提前实现或承诺 macOS/Linux 桌面包;Docker 路线继续维护。
- 本项目普通开发、构建及交付产物必须允许项目所有者和现有 agent 开发账号正常访问。新建普通暂存目录应继承项目权限,禁止把私有临时目录的仅创建者 ACL 随移动带入长期目录或发行包;不得为修复此问题放开整块磁盘或 Everyone 权限。数据库口令、控制令牌等明确的凭据保护仍单独保留,不能与普通产物权限混为一谈。
生成代码必须遵守:
- 所有文件编码 UTF-8(无 BOM)
- 禁止 UTF-16 / GBK
- 中文直接输出,不允许 \uXXXX
- 文件写入必须使用 UTF-8
2. 工具与实施规则
- 默认使用
apply_patch编辑文件。 - Shell 仅用于:
- 测试/构建/静态检查
- 读取运行态信息
- 无专用工具可替代的命令
- 禁止提交调试残留、临时脚本、敏感信息。
- 未经确认禁止新增依赖。
- 所有外部调用与 I/O 必须有错误处理(后端日志 / 前端
console.error)。
3. 仓库卫生与临时空间
- 开发、测试和清理任务必须遵守根目录
REPOSITORY_HYGIENE.md。原因:统一入口能让各类任务按同一套数据保护和清理边界执行。 - 新临时产物统一放在
.tmp/<用途>/<任务标识>/,任务结束清理自有可重建文件;保留项说明用途、大小与到期日。原因:按任务归档便于确认归属、追踪占用并安全收尾。 - 通用任务新增的任务专属可重建临时产物默认预算为 2 GiB;共享依赖缓存及登记批准留存的验收夹具另账,不计入该预算,但须盘点并报告
.tmp全部实际占用。轻量失败诊断最多保留 7 天且每用途最近 3 次,带业务状态的失败验收夹具到期只触发复核,不按此期限自动删除。磁盘剩余不足 10 GiB 或 5% 时暂停新增重型产物并报告;预算超额本身不授权删除。原因:预算限制任务新增成本,单独记录共享资产和验收证据可避免因物理占用超额而误删;低磁盘阈值保护实际可用空间。- 本任务特例(2026-09-12 用户明确授权):便携 Launcher 自动落地任务取消单任务 512 MiB、
.tmp2 GiB 等容量上限,不再因容量预算重复请求确认。仍须盘点/复用/收尾,保留低磁盘暂停、期限、在用文件和真实数据保护;不改变其他任务的默认卫生规则。原因:特批仅放开容量限制,不能扩大到删除授权或数据风险。
- 本任务特例(2026-09-12 用户明确授权):便携 Launcher 自动落地任务取消单任务 512 MiB、
- 查看、分析不代表授权删除。清理历史文件前列出准确路径、用途和预计释放空间并取得确认;禁止整仓库通配清理,禁止删除业务数据、任务与通知记录、登录态和在用文件。原因:盘点不能代替删除许可,精确范围可避免误删用户数据和运行状态。
- 交付时检查临时产物残留和 Git 差异;文档中的限额不等于已经实现自动清理,不得虚报已启用的保护能力。原因:检查可发现遗留和意外改动,也能区分纸面要求与真实保护行为。
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.
- 1mo ago First seen · 50 lines · 1,169 tokens per session scan A 6898b21e0bb9
ai-goofish-monitor-QB AGENTS.md is an instructions file published in the GitHub repository banbanzhige/ai-goofish-monitor-QB (123 stars, last pushed 18d ago), licensed MIT. It adds 1,169 tokens to every session, about $0.0047 per session on Opus 5.5. 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 2026-09-29.
ai-goofish-monitor-QB AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-goofish-monitor-QB AGENTS.mdbanbanzhige/ai-goofish-monitor-QB | Instructions file | 123 | 18d ago | MIT | A | 1,169 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |